io.github.DigbyO/colour-memory

Est-ce que io.github.DigbyO/colour-memory est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.DigbyO/colour-memory » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 92 outils

• accessibility_check≈ 199 tokens

  Evaluates contrast for a single foreground/background pair. For palettes or multiple colours, use accessibility_matrix instead, it replaces multiple accessibility_check calls in one response.

  Paramètres, retour & exemple (2)

  Paramètres

  • hex_val · string · requis
    Foreground hex value
  • background · string · optionnel
    Background hex (default 'FFFFFF')

  Exemple d'appel

  {"name": "accessibility_check", "arguments": {"hex_val": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• accessibility_font≈ 204 tokens

  Given a background hex and a palette of candidate foreground colours, return them ranked by contrast ratio with WCAG grades and specific recommendations for body text, large text, and UI components.

  Paramètres, retour & exemple (2)

  Paramètres

  • palette · array · requis
    Candidate foreground hex values
  • background · string · requis
    Background hex value

  Exemple d'appel

  {"name": "accessibility_font", "arguments": {"palette": [], "background": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• accessibility_matrix≈ 216 tokens

  Accept a palette array and return every foreground/background combination with contrast ratio, AA normal, AA large, AAA normal, AAA large pass/fail grades, and a summary. Use this instead of calling accessibility_check multiple times for a palette.

  Paramètres, retour & exemple (1)

  Paramètres

  • palette · array · requis
    Array of hex values e.g. ['#D4A829', '#1A5C6E', '#0F2D6B', '#0A0A0B']

  Exemple d'appel

  {"name": "accessibility_matrix", "arguments": {"palette": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• accessibility_rules≈ 190 tokens

  Convert a palette WCAG matrix into actionable design-system rules. Returns safe pairs, AA-only pairs, large-text-only pairs, decorative-only pairs, best text colour per background, and component usage rules. Deterministic, no LLM cost.

  Paramètres, retour & exemple (1)

  Paramètres

  • palette · array · requis
    Array of hex values

  Exemple d'appel

  {"name": "accessibility_rules", "arguments": {"palette": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• accessibility_simulate≈ 222 tokens

  Return simulated hex values for full-severity protanopia, deuteranopia and tritanopia only, using the Machado, Oliveira & Fernandes (2009) model (severity 1.0, linear sRGB), with a flag when a simulated colour had to be clipped to sRGB. Anomalous trichromacy and partial severities are not simulated. A model prediction on a standard display, not how an individual perceives colour.

  Paramètres, retour & exemple (1)

  Paramètres

  • hex_val · string · requis
    Hex value e.g. '#BE0032'

  Exemple d'appel

  {"name": "accessibility_simulate", "arguments": {"hex_val": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• agent_brief≈ 940 tokens

  Generate a complete colour direction package for another AI agent or image generation model. Fetches a historically grounded archive palette from the concept, then produces: an agent brief (colour direction in prose), colour tokens with hex values and roles, a model-specific image generation prompt, a negative prompt, and lighting notes. Supports midjourney, flux, dalle, stable_diffusion. Example: task='luxury hotel bedroom', concept='Ottoman winter luxury', model='midjourney'. Use this to make Colour Memory the colour layer for other AI systems. Archive-grounded retrieval is evidence-filtered: entries with claim_role='reject' (no primary source and no period connection), stub entries, blank-source entries, and entries below minimum_claim_strength are never selected. If fewer than palette_size colours pass these filters, the call returns an honest incomplete result (ok:false, error_code:INSUFFICIENT_EVIDENCE_ELIGIBLE_PALETTE) rather than padding the palette with rejected or weak evidence. Negative constraints (from 'avoid' or negation phrases in concept like 'must never', 'without', 'not') are also applied to retrieval, not just flagged afterward -- a brief that says a wedding must never feel funereal will not surface mourning-themed colours in the first place. locked_palette calls skip evidence filtering entirely since the caller is supplying colours directly, not requesting archive evidence.

  Paramètres, retour & exemple (10)

  Paramètres

  • task · string · requis
    What the other AI needs to generate e.g. 'luxury hotel bedroom image'
  • avoid · array · optionnel
    Optional: terms/associations to keep out of retrieval e.g. ['mourning', 'funeral black']. Affects retrieval directly, not just post-hoc flagging.
  • model · string · optionnel
    Target model: midjourney, flux, dalle, stable_diffusion
  • archive · string · optionnel
    Optional: restrict palette query to this archive e.g. georgianpleasures, japan, china
  • concept · string · requis
    Colour concept to draw from e.g. 'Ottoman winter luxury', 'Victorian mourning'. Negation phrases ('must never', 'without', 'not X') are extracted and kept out of retrieval.
  • style_notes · string · optionnel
    Optional: additional style direction e.g. 'matte surfaces only', 'no gold'
  • palette_size · integer · optionnel
    Number of archive colours to include (default 5, max 8)
  • locked_palette · array · optionnel
    Optional: list of hex values to use exclusively. When provided, no archive query is run and no evidence filtering applies — these exact colours are used as-is. Prevents palette drift.
  • allowed_archives · array · optionnel
    Optional: list of allowed archive names. Query restricted to these archives only.
  • minimum_claim_strength · string · optionnel · A | B | C | D | E
    Evidence-grade floor for archive-grounded retrieval (default 'C'). Grade controls documentary strength; claim_role='reject' entries are excluded regardless of how low this is set. Not applied to locked_palette calls.

  Exemple d'appel

  {"name": "agent_brief", "arguments": {"task": "texte", "concept": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• agent_verify≈ 292 tokens

  Verify that an AI-generated image actually used the colours specified in an agent_brief call. Supply the generated image (URL or base64) and the target palette from agent_brief colour_tokens. Returns a fidelity score 0-100, dE2000 distance per colour, match quality per colour (accurate/acceptable/drifted/ignored), and an overall verdict. Use after agent_brief + image generation to close the colour loop.

  Paramètres, retour & exemple (3)

  Paramètres

  • image_url · string · optionnel
    URL of the generated image
  • image_base64 · string · optionnel
    Base64 encoded generated image
  • target_palette · array · requis
    Hex values from agent_brief colour_tokens e.g. ['#ED9921', '#E29937']

  Exemple d'appel

  {"name": "agent_verify", "arguments": {"target_palette": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• archive_cliche≈ 333 tokens

  Find the most surprising archive colour for a concept and generate a memorable one-liner subverting the obvious expectation. Supply a concept (e.g. 'love', 'grief', 'luxury', 'power') and optionally the expected colour (e.g. 'red' for love). The archive finds the contradiction and Claude writes the one-liner, short story, and tweet. Example: love + red returns Shakespeare's dark green with 'Love is not red. It is the green of someone still waiting in a field.' Use this for public-facing demos, content, and brand storytelling.

  Paramètres, retour & exemple (3)

  Paramètres

  • concept · string · requis
    Colour concept to subvert e.g. 'love', 'grief', 'luxury', 'betrayal', 'power'
  • n_results · integer · optionnel
    Number of archive entries to search (default 8)
  • expected_colour · string · optionnel
    Optional: the cliche colour to contradict e.g. 'red', '#FF0000'. Hex or colour name.

  Exemple d'appel

  {"name": "archive_cliche", "arguments": {"concept": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• archive_coverage_gap≈ 300 tokens

  Given a list of themes, report which are well-evidenced in the archive and which are under-evidenced or missing. Returns a coverage matrix: for each theme, entries found, coverage grade (strong/moderate/weak/missing), best match with claim strength, and what source type would be needed to improve coverage. Use this BEFORE building an archive_report_brief or brief_forensic to know where the evidence is strong and where gaps will appear. Prevents building beautiful reports that quietly ignore half the brief.

  Paramètres, retour & exemple (2)

  Paramètres

  • themes · array · requis
    Themes to check e.g. ['opium', 'gin', 'gambling', 'racing']
  • archives · array · optionnel
    Optional archives to search e.g. ['EIC', 'Dickens']

  Exemple d'appel

  {"name": "archive_coverage_gap", "arguments": {"themes": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• archive_cultural_anachronism≈ 363 tokens

  Check a list of colour entries for anachronism risk. Detects whether the primary source date falls outside the requested period, whether the archive is a known modern source (RacingSilks, FootballStrips), and returns a period_relevance score and safe phrasing. Essential for historical documents: prevents a 2011 Jockey Club racing silk registration being presented as Georgian evidence. Returns anachronism_risk (none/low/medium/elevated/high), period_relevance score 0-1, safe_phrasing, and unsafe_phrasing for each entry.

  Paramètres, retour & exemple (4)

  Paramètres

  • entries · array · requis
    Colour entries to check
  • period_end · integer · optionnel
    End year e.g. 1830
  • period_start · integer · optionnel
    Start year e.g. 1714
  • target_period · string · optionnel
    Period description e.g. 'Georgian England 1714-1830'

  Exemple d'appel

  {"name": "archive_cultural_anachronism", "arguments": {"entries": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• archive_evidence_gap≈ 368 tokens

  Given a hex value and a proposed claim about it, return whether the archive supports that claim, what is missing, what kind of source would be needed, and safe agent wording. This is Colour Memory's anti-hallucination endpoint. It turns the absence of evidence into a forensic finding rather than a gap to fill with invention. Example: hex #4A535C + proposed claim 'cyanosis in a death chamber' returns: nearest archive support, support level (supported/partial/unsupported), what source type is needed, and safe wording for the agent to use. Essential for museum, documentary, editorial, legal, and forensic workflows.

  Paramètres, retour & exemple (4)

  Paramètres

  • hex · string · requis
    Hex colour to analyse e.g. '#4A535C'
  • archive · string · optionnel
    Optional archive to search e.g. 'DarkHistory'
  • n_candidates · integer · optionnel
    Number of archive candidates to return (default 5)
  • proposed_claim · string · requis
    What you want to say about this colour e.g. 'cyanosis in a death chamber'

  Exemple d'appel

  {"name": "archive_evidence_gap", "arguments": {"hex": "texte", "proposed_claim": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• archive_provenance≈ 246 tokens

  Explains the provenance of a named archive colour: documented fact vs computational derivation vs cultural interpretation, with confidence and citation format. This is one component of colour_passport, but also a standalone research tool for deep provenance work (museum, documentary, editorial). Use colour_passport for a general profile; call this directly for research workflows needing full source-chain detail.

  Paramètres, retour & exemple (1)

  Paramètres

  • colour_name · string · requis
    Name of the archive colour e.g. 'Love Idleness', 'Woad Vat Blue', 'Murex Luxury'

  Exemple d'appel

  {"name": "archive_provenance", "arguments": {"colour_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• archive_report_brief≈ 1018 tokens

  One-call complete archive research package for a document, PDF, or editorial brief. Input: title, audience, themes, archives to draw from, things to avoid, number of colours. Output: ranked colour cards with full provenance, story order, source confidence flags, pull quote, CTA line, CSS tokens, image prompt for Midjourney/Flux/DALLE, editorial argument, weakest and strongest entries identified. Replaces chaining archive_search + get_colour_card + cliche_breaker + agent_brief separately. Two Claude calls total. This is the endpoint for building premium archive documents, PDFs, briefs, and editorial content. Use this first for any document workflow.

  Paramètres, retour & exemple (16)

  Paramètres

  • avoid · array · optionnel
    Topics to suppress e.g. ['arsenic wallpaper', 'Wedgwood blue']
  • title · string · optionnel
    Document title e.g. 'The Colours of Georgian Power'
  • themes · array · requis
    Research themes e.g. ['racing silks', 'EIC trade', 'Keats']
  • archives · array · optionnel
    Archives to search e.g. ['RacingSilks', 'EIC', 'Keats', 'Dickens']
  • audience · string · optionnel
    Target audience e.g. 'serious Georgian collector'
  • n_colours · integer · optionnel
    Number of colours to return (default 8, max 16)
  • period_end · integer · optionnel
    Hard period gate: exclude entries dated after this year. Default 9999 (no upper bound).
  • period_start · integer · optionnel
    Hard period gate: exclude entries dated before this year. Default 0 (no lower bound).
  • allow_partial · boolean · optionnel
    If false (default), returning fewer cards than requested sets ok=false with error_code INSUFFICIENT_PALETTE_RESULTS instead of a silent short 'success'. Set true to accept a short result.
  • output_format · string · optionnel
    Reserved for future use -- currently accepted but has no effect on the response shape (the endpoint always returns the full report).
  • strict_sources · boolean · optionnel
    Only return entries with named primary sources (default true)
  • family_card_mode · string · optionnel · auto | always | conservative
    How near-identical cultivars/records are presented. 'auto' (default): current behaviour, groups into family cards above the standard ΔE threshold. 'always': widens the clustering threshold so more near-duplicates group into family cards. 'conservative': suppresses family cards over max_family_card_share of the deck, instead promoting one hero cultivar per suppressed family with the rest folded into that card's also_supported_by list (never dissolved back into separate near-duplicate swatches).
  • confidence_threshold · number · optionnel
    Minimum confidence score (0.0-1.0) for an entry to be included. Default 0.5 filters out weakly-matched stubs.
  • max_family_card_share · number · optionnel
    Conservative mode only: maximum fraction (0.0-1.0, default 0.5) of presented cards that may be family cards before excess families are suppressed to hero cards. Ignored in auto/always modes.
  • minimum_claim_strength · string · optionnel
    Hard evidence-grade floor: A, B, C, D, or E. Never silently relaxed.
  • strict_semantic_colour · boolean · optionnel
    Default false. When true, excludes entries whose quoted colour language contradicts their stored hex (e.g. a record naming 'Prussian blue' whose hex is actually a pale cream) rather than presenting them as normal evidence. Never alters hex values, only excludes flagged ones.

  Exemple d'appel

  {"name": "archive_report_brief", "arguments": {"themes": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• archive_report_document≈ 598 tokens

  Create a designed, full-colour Word (.docx) report from Colour Memory records. Use this whenever the user asks for a document, report, write-up, handout or Word file built from archive findings, instead of writing a plain document yourself. Pass the records by the record_id or slug exactly as archive_search (or another tool) returned them, grouped into sections with a heading and optional narrative. Colour Memory resolves every record itself and draws its name, date, place, notes, evidence grade and source from the archive: no evidence field is accepted from the caller, and an unknown or ambiguous reference refuses the whole document (REPORT_RECORD_NOT_RESOLVED). Colour is shown honestly: a filled chip only where the record has a hex, always with where that hex comes from; otherwise the colour appears as the source's own words in an empty frame. Narrative you write is printed in blocks labelled as interpretation, never as archive evidence. Returns a signed, time-limited download link (delivery='url', default) or the file inline (delivery='base64'). Limits: 8 sections, 6 records per section.

  Paramètres, retour & exemple (4)

  Paramètres

  • title · string · requis
    Document title, under 90 characters.
  • delivery · string · optionnel · url | base64
    url (default) or base64.
  • sections · array · requis
    Ordered sections of the report.
  • subtitle · string · optionnel
    One-sentence subtitle.

  Exemple d'appel

  {"name": "archive_report_document", "arguments": {"title": "texte", "sections": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• archive_search≈ 832 tokens

  Full-text keyword search across all archive colour names and notes. Find colours by name fragment, material, cultural reference, pigment type, or historical period. Complements conceptual embedding search with exact keyword matching. Examples: 'cerulean' (28 matches, e.g. Bourton Cerulean), 'Prussian' (187 matches spanning pigment history), 'medieval' (over 1,000 matches across period archives). Never returns a bare empty result for a genuinely obscure query -- result_path in the response is 'direct' (exact keyword hit), 'broadened' (archive restriction dropped), or 'redirected' (fell back to conceptual/semantic search) so you always know which one fired. Set entity_mode='exact' to search by botanical identity rather than by word: a plain query for 'Rose' matches any cultivar name containing it (including Sweet Peas called 'Rose Pink'), whereas entity_mode='exact' returns genus Rosa only and discloses how many off-genus records were excluded.

  Paramètres, retour & exemple (9)

  Paramètres

  • limit · integer · optionnel
    Alias for n_results
  • query · string · requis
    Search term e.g. cerulean, Prussian, Ottoman, ochre, medieval
  • offset · integer · optionnel
    Skip this many ranked matches before returning results -- collection paging. The response's next_offset gives the value to pass here for the next page; it is absent on the last page. total_found always reports the full collection size.
  • archive · string · optionnel
    Optional archive filter e.g. oxfordshire, japan, pigment, keats, eic, racingsilks
  • year_to · integer · optionnel
    Boost entries on or before this year e.g. 1600 for Renaissance, 1901 for Victorian
  • n_results · integer · optionnel
    Results per page (default 10, max 50 per call). This is a PAGE size, not a collection limit -- for a large collection (tens or hundreds of records) page with offset until next_offset disappears, and never tell the user the product caps out at one page.
  • year_from · integer · optionnel
    Boost entries on or after this year e.g. 1400 for Renaissance, 1837 for Victorian
  • entity_mode · string · optionnel · text | exact
    'text' (default): ordinary keyword search -- 'rose' finds any name containing the word, across genera. 'exact': resolve the query to a botanical entity and return ONLY records whose structured identity matches. Use 'exact' when you mean the plant, not the word: entity_mode='exact' with query='Rose' returns genus Rosa only and excludes Sweet Pea cultivars named 'Rose Pink'. The response carries an entity_resolution block showing the resolved genus and how many off-genus rows were excluded.
  • include_full · boolean · optionnel
    Return complete notes and source fields. Default false returns 150-char snippets. Set true for report workflows.

  Exemple d'appel

  {"name": "archive_search", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• brand_asset_pack≈ 265 tokens

  Complete brand asset pack. Returns CSS variables, Tailwind config, Figma tokens JSON, citation cards, and a Markdown brand guide. Everything a brand team needs to ship. Deterministic. No LLM cost.

  Paramètres, retour & exemple (5)

  Paramètres

  • market · string · optionnel
    Target market
  • medium · string · optionnel
    digital | print | both
  • palette · array · requis
    Hex values
  • use_case · string · optionnel
    Use case
  • brand_category · string · optionnel
    Optional brand name or category

  Exemple d'appel

  {"name": "brand_asset_pack", "arguments": {"palette": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• brand_audit≈ 972 tokens

  Fast, fully deterministic brand colour audit. Accepts a palette array plus market, use_case, medium and brand_category. COMPUTED SYNCHRONOUSLY, no model call of any kind: colour roles with archive names, the full WCAG accessibility matrix, cultural risk per colour, CSS variables, Tailwind config, design tokens and production notes. NOT COMPUTED HERE: palette interpretation -- the verdict, its score and the written narrative copy. Those require an LLM call and used to be made inside this tool without saying so, which put a normal five-colour audit at 43-45s. The palette_verdict and verdict_copy keys are still returned, carrying interpretation_status='not_computed' plus a ready-to-send palette_verdict.continuation.arguments -- forward those verbatim to the palette_verdict tool to get the interpretation. Replaces chaining accessibility_matrix + cultural_risk_assessment; palette_verdict is now an explicit, optional second call rather than a hidden one. FOR A LIVE-SITE BRAND AUDIT ('audit this website'): inspect representative rendered pages FIRST (homepage, about, one deep page) and pass what you observed as site_evidence -- a CSS scrape alone is not an audit of what a visitor sees, and the response's audit_evidence.audit_status will say PARTIAL until real multi-page rendered evidence is supplied. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (6)

  Paramètres

  • market · string · optionnel
    Target market e.g. 'UK luxury', 'global', 'Japan'
  • medium · string · optionnel
    digital | print | both
  • palette · array · requis
    Array of hex values e.g. ['#D4A829', '#1A5C6E', '#0F2D6B', '#0A0A0B']
  • use_case · string · optionnel
    Use case e.g. 'brand identity', 'packaging', 'app UI'
  • site_evidence · object · optionnel
    Evidence for a LIVE-SITE audit, supplied by the host (Colour Memory does not browse). {pages: [{url, role: 'homepage'|'about'|'work'|'services'|'product'|..., screenshot: bool, tokens: bool, observations: [{hex, evidence_type: 'canonical_token'|'rendered_observation'|'source_verified_external'|'model_interpretation', prominence?: 'dominant'|'primary'|...}]}], competitors: [{name, colours: [hex], colour_provenance: 'verified_brand_guideline'|'verified_current_site'|'verified_identity_source'|'estimated'|'unverified', source?}]}. A FULL live-site audit needs a homepage, an about/company page and one meaningful deep page (work/approach/services/product/case study), with rendered evidence from at least two of them. Supply less and the response's audit_evidence.audit_status comes back PARTIAL or INSUFFICIENT with the specific gaps named -- it will not present as a completed multi-page audit. A competitor colour that is not verified is kept as a QUALITATIVE comparison and never enters a CIEDE2000 or distinctiveness number; do not invent a hex to fill the gap.
  • brand_category · string · optionnel
    Optional brand category e.g. 'developer tool', 'food', 'fashion'

  Exemple d'appel

  {"name": "brand_audit", "arguments": {"palette": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• brand_collision≈ 527 tokens

  Can this brand own this colour against these competitors in this market? Input: brand hex, brand name, competitor hexes and names, market, region. Returns CIEDE2000 distance to each competitor, archive context for each colour, a distinctiveness score (0-100), an ownership verdict (strong/viable/contested/collision), a plain-English verdict summary, and a strategic recommendation. Use before committing to a brand colour in a competitive market. Replaces manual colour distance checks and competitor palette analysis.

  Paramètres, retour & exemple (7)

  Paramètres

  • market · string · optionnel
    Market context e.g. 'UK luxury food retail'
  • region · string · optionnel
    Region code e.g. 'GB', 'UAE', 'JP'
  • brand_hex · string · requis
    Brand hero colour hex e.g. '#D4A829'
  • brand_name · string · optionnel
    Brand name e.g. 'Fortnum and Mason'
  • competitor_hexes · array · optionnel
    List of competitor hex colours
  • competitor_names · array · optionnel
    Competitor names matching hex order
  • competitor_provenance · array · optionnel
    Where each competitor colour came from, positionally aligned to competitor_hexes. Only a verified value moves the distinctiveness score; an estimated or unverified one is kept as a QUALITATIVE comparison instead. Never invent a hex to fill a gap -- omit the competitor's colours and name them qualitatively. Omit this array entirely and the numbers are computed as before, with every competitor labelled 'unverified'.

  Exemple d'appel

  {"name": "brand_collision", "arguments": {"brand_hex": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• brand_guideline_claims≈ 365 tokens

  Resolves claim_id values (returned inline on every colour by brand_guideline_specify and brand_guideline_select) into their full claim record: source title/locator/citation, the exact permitted claim text, do_not_say restrictions, and claim_role (anchor/analogue/reject). Read-only -- reads the already-persisted, frozen brand_ref snapshot, never re-runs generation or mutates anything. Omit claim_ids to return every claim on the brand_ref. Accepts exactly one of brand_ref or project_id, same as brand_guideline_pdf.

  Paramètres, retour & exemple (4)

  Paramètres

  • brand_ref · string · optionnel
    The brand_ref returned by brand_guideline_specify or brand_guideline_select.
  • claim_ids · array · optionnel
    Which claim_id values to resolve. Omit (or pass an empty list) to return every claim on the brand_ref.
  • project_id · string · optionnel
    Alternative to brand_ref for an authenticated (keyed) brand project. Requires the same API key that created it.
  • project_version · integer · optionnel
    Resolve claims against this specific immutable version instead of the project's current version.

  Exemple d'appel

  {"name": "brand_guideline_claims", "arguments": {"brand_ref": "texte", "claim_ids": [], "project_id": "texte", "project_version": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• brand_guideline_pdf≈ 525 tokens

  Renders a client-facing brand colour standard from an existing brand_ref. The document covers the direction carried forward and its assessment, the colour system in proportion, the argument for the palette, packaging and digital application, a full pairwise WCAG accessibility matrix computed upstream (never hand-drawn examples), and a provenance and evidence register in which every claim is bound to the colour it belongs to. Page count is not fixed: sections that have nothing real to say are omitted rather than padded -- a single-candidate brand_ref drops the comparison spread, and a candidate that was never scored for distinctiveness gets a different page shape rather than an empty scale. Derived colours are never presented in documented-source language. Renders the brand_guideline_select-chosen candidate if one has been recorded, otherwise the strongest eligible candidate as a provisional preview (clearly labelled as such). Reads only the already-persisted, frozen snapshot -- never re-runs brand_guideline_specify, never rematches an archive, never mutates the resolved project. Accepts exactly one of brand_ref or project_id.

  Paramètres, retour & exemple (4)

  Paramètres

  • delivery · string · optionnel · url | base64
    'url' (default): signed, time-limited R2 download link. 'base64': PDF bytes returned inline.
  • brand_ref · string · optionnel
    The brand_ref returned by brand_guideline_specify or brand_guideline_select.
  • project_id · string · optionnel
    Alternative to brand_ref for an authenticated (keyed) brand project. Requires the same API key that created it.
  • project_version · integer · optionnel
    Render this specific immutable version instead of the project's current version. Omit to render the current version.

  Exemple d'appel

  {"name": "brand_guideline_pdf", "arguments": {"delivery": "url", "brand_ref": "texte", "project_id": "texte", "project_version": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• brand_guideline_select≈ 390 tokens

  Records which brand_guideline_specify candidate was chosen, which colours should be locked for future iteration, and which claims should be suppressed -- produces a revised brand_ref (same reference, a new version underneath it, exactly like a versioned house_ref). No accounts or reviewer states yet -- this demonstrates decision-making, not a full approval workflow.

  Paramètres, retour & exemple (6)

  Paramètres

  • note · string · optionnel
    Optional free-text rationale, e.g. "Client prefers the quieter system."
  • brand_ref · string · optionnel
    The brand_ref returned by brand_guideline_specify. Supply this OR project_id.
  • project_id · string · optionnel
    The project_id returned by brand_guideline_specify. Use this after a refinement (a continued project has a project_id but no new brand_ref). Supply this OR brand_ref.
  • locked_colour_ids · array · optionnel
    colour_id values to lock for future iteration.
  • suppressed_claim_ids · array · optionnel
    claim_id values to suppress (marked superseded).
  • selected_candidate_id · string · requis
    Which candidate_id to make canonical.

  Exemple d'appel

  {"name": "brand_guideline_select", "arguments": {"selected_candidate_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• brand_guideline_specify≈ 1793 tokens

  Generates the case for a brand's colours, not just the colours themselves: three genuinely different, archive-grounded candidate palettes from a brand brief, each scored for distinctiveness against named competitors, checked for accessibility, and labelled with exactly what each colour can and cannot legitimately claim (documented archive anchor vs analogue vs original brand colour). Returns a brand_ref (valid 24h) plus a claim_id per colour -- resolve those into full source/permitted-claim/do_not_say text with brand_guideline_claims (the response's own claim_detail_available_via field always names it explicitly). Follow with brand_guideline_select to record which candidate was chosen. CREATE ONCE, THEN VERSION: the response returns project_id and current_version. When you refine or update a Brand Standard you already created in this conversation, pass that project_id back as continue_project_id rather than creating a second project. TIMING (2026-08-07): real generation cost ranges roughly 60-280 seconds depending on retrieval/generation path. This call races generation against a safe ~55s window: a fast generation returns the full result exactly as described above, unchanged. A slower generation instead returns a compact {"status": "processing", "brand_job_ref": ..., "poll_after_seconds": ...} -- generation keeps running server-side regardless, and is never lost. Call brand_guideline_status with that brand_job_ref to retrieve the completed result (brand_ref, project_id, candidate summary) once ready; poll no more often than poll_after_seconds suggests.

  Paramètres, retour & exemple (8)

  Paramètres

  • brand_name · string · requis
    The brand's name.
  • brand_brief · object · optionnel
    Category, positioning, audience, personality, values, channels, markets, and named competitors with their hex colours.
  • constraints · object · optionnel
    Structured negative/positive retrieval constraints, checked before archive-diversity capping. avoid_concepts takes precedence over any sentiment inferred from brand_brief prose.
  • preferences · object · optionnel
  • palette_input · object · requis
    Exactly how to source the candidate colours.
  • identity_assets · object · optionnel
  • output_preferences · object · optionnel
  • continue_project_id · string · optionnel
    The project_id returned by an earlier call, when this is a REFINEMENT of that same Brand Standard. Reuse it and the work joins that project as a new version; omit it and a second project is created. 'Make it warmer', 'change the secondary', 'render the PDF again' and 'show another option' are all continuations. Start a new project only when the customer asks for a genuinely separate brand.

  Exemple d'appel

  {"name": "brand_guideline_specify", "arguments": {"brand_name": "texte", "palette_input": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• brand_guideline_status≈ 326 tokens

  Resolves a brand_job_ref returned by brand_guideline_specify when its race-to-complete window elapsed before generation finished. Read-only, in-process lookup -- never re-runs generation. Returns {"status": "processing"} if still running, {"status": "complete", "brand_ref": ..., "project_id": ..., "recommended_candidate_id": ..., "candidate_count": ...} once done (a compact summary -- use the returned brand_ref with brand_guideline_select/brand_guideline_pdf/brand_guideline_claims for full detail, the same pattern every other Brand Standard tool already uses), or {"status": "failed", "error_code": ..., "message": ...} if generation genuinely failed server-side. An unknown or expired brand_job_ref returns a structured BRAND_JOB_NOT_FOUND error, never a crash or empty success.

  Paramètres, retour & exemple (1)

  Paramètres

  • brand_job_ref · string · requis
    The brand_job_ref returned by brand_guideline_specify's processing response.

  Exemple d'appel

  {"name": "brand_guideline_status", "arguments": {"brand_job_ref": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• brand_report≈ 441 tokens

  One-call complete brand colour intelligence report. Input: hex + brand context + markets + medium + product type. Output: archive anchor, cliche contradiction, colour DNA, strategy verdict, commercial signals, market reading per market, usage rules, palette roles, ecommerce copy, memory hooks, Instagram caption, and Midjourney/Flux/DALLE agent brief. Use this instead of chaining colour_strategy + cliche_breaker + ecommerce_product_copy + memory_hooks + agent_brief separately. Two Claude calls total. One complete response.

  Paramètres, retour & exemple (7)

  Paramètres

  • hex · string · requis
    Hero hex colour e.g. '#4A2A50'
  • medium · string · optionnel
    Medium e.g. 'packaging', 'digital', 'interior'
  • concept · string · optionnel
    Optional concept to search for cliche contradiction e.g. 'luxury', 'eco', 'wellness'
  • markets · array · optionnel
    Target markets e.g. ['UK', 'France', 'Japan']
  • product_type · string · optionnel
    Product type for copy e.g. 'velvet cushion', 'fragrance', 'cleaning spray'
  • target_model · string · optionnel
    Image model for agent brief e.g. 'midjourney', 'flux', 'dalle'
  • brand_context · object · optionnel
    Brand context: category, positioning, audience, channels

  Exemple d'appel

  {"name": "brand_report", "arguments": {"hex": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• brand_system≈ 396 tokens

  Complete brand colour system in one call. Returns colour roles with archive names, light and dark mode role maps, typography guidance, usage rules per colour, design tokens (CSS, Tailwind, Figma), and citation cards. Deterministic. No LLM cost. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (5)

  Paramètres

  • market · string · optionnel
    Target market e.g. global, UK, Japan
  • medium · string · optionnel
    digital | print | both
  • palette · array · requis
    Hex values
  • use_case · string · optionnel
    Use case e.g. brand identity, packaging
  • brand_category · string · optionnel
    Optional e.g. developer tool, luxury, food

  Exemple d'appel

  {"name": "brand_system", "arguments": {"palette": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_card≈ 189 tokens

  Look up a named colour and return its hex, archive, provenance, and cultural notes.

  Paramètres, retour & exemple (2)

  Paramètres

  • name · string · optionnel
    Colour name e.g. 'Prussian Blue' or 'Ottoman Carbon Ink'
  • slug · string · optionnel
    Stable colour slug from archive_search e.g. 'keats:keats-s-lung' -- preferred over name for reliable retrieval

  Exemple d'appel

  {"name": "colour_card", "arguments": {"name": "texte", "slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_combination≈ 222 tokens

  Assess 2-5 colours as a combination for a given context (UI, data viz, fashion, interior, print, branding). Returns harmony type, clash warnings, contrast summary, and specific deployment rules for the context.

  Paramètres, retour & exemple (2)

  Paramètres

  • colours · array · requis
    2-5 hex values to assess as a combination
  • context · string · optionnel
    Usage context: UI | data viz | fashion | interior | print | branding

  Exemple d'appel

  {"name": "colour_combination", "arguments": {"colours": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_compare≈ 268 tokens

  Deep perceptual and semantic comparison between any two hex values. Returns quantified differences in LRV, chroma, hue angle, warmth, and CIEDE2000 distance, plus cultural context on both — which is more authoritative, more saturated, more stable under different illuminants, and what each has historically signified. Use when choosing between two colours or explaining why one works better than another. Not a harmony tool — this is a decision and reasoning tool.

  Paramètres, retour & exemple (2)

  Paramètres

  • hex_a · string · requis
    First colour hex e.g. '#003366'
  • hex_b · string · requis
    Second colour hex e.g. '#1877F2'

  Exemple d'appel

  {"name": "colour_compare", "arguments": {"hex_a": "texte", "hex_b": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_cultural_risk≈ 282 tokens

  Cultural risk assessment for a hex value or palette (symbolic weight, regional taboos, religious associations, market flags). This is one component of colour_passport for single colours. Use colour_passport for a general profile; call this directly for palette-level risk checks or when cultural risk is the only thing being asked about.

  Paramètres, retour & exemple (3)

  Paramètres

  • hex · string · optionnel
    Single hex value to assess e.g. '#FF9900'
  • markets · array · optionnel
    Optional market focus e.g. ['China', 'Middle East', 'India']
  • palette · array · optionnel
    Optional list of hex values to assess as a palette

  Exemple d'appel

  {"name": "colour_cultural_risk", "arguments": {"hex": "texte", "markets": [], "palette": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_dna≈ 282 tokens

  Compact semantic fingerprint for a single hex colour. This is one component of colour_passport. Use colour_passport for a general colour profile; use this only when the user explicitly wants the fingerprint format alone. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (1)

  Paramètres

  • hex · string · requis
    Hex colour to fingerprint e.g. '#4A2A50'

  Exemple d'appel

  {"name": "colour_dna", "arguments": {"hex": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_forensics≈ 401 tokens

  Assess whether a hex colour can be safely specified for a physical application. Returns: specification_safe verdict (yes / conditional / avoid), risks, required actions, light behaviour under three illuminants (north daylight, warm artificial, direct sun), substrate-specific notes, and a recommended alternative. Backed by CIEDE2000 archive matching and Claude material knowledge. Examples: ultramarine on lime plaster, lead white on exterior timber, verdigris on north-facing interior wall, red ochre on historic brick.

  Paramètres, retour & exemple (5)

  Paramètres

  • hex · string · requis
    Hex colour to assess e.g. '#2A5498'
  • use · string · optionnel
    Specific use context e.g. 'heritage repair', 'new build interior', 'conservation project'
  • finish · string · optionnel
    Paint finish e.g. 'matt', 'eggshell', 'gloss', 'limewash'
  • substrate · string · requis
    Physical substrate e.g. 'lime plaster', 'gypsum board', 'brick', 'timber', 'canvas'
  • orientation · string · optionnel
    Room or surface orientation e.g. 'north-facing', 'south exterior', 'east bedroom'

  Exemple d'appel

  {"name": "colour_forensics", "arguments": {"hex": "texte", "substrate": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_harmonies≈ 456 tokens

  Return complementary, triadic, analogous, and split-complementary harmonies matched to named archive colours. Also available: 'hay_contrast' -- D.R. Hay's (1838) documented contrast pairing between six named hues (yellow/purple, orange/blue, red/green), with Field's proportional power for the pair. Unlike the fixed-angle types, this snaps the input to Hay's nearest named hue rather than rotating it, and returns covered:false with no invented partner when the input sits nearer a tertiary region (olive/citron/russet) than any of the six -- Hay records only an aggregate total for tertiaries, never a specific pair. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (2)

  Paramètres

  • hex · string · requis
    Hex value e.g. '#3A5C8C'
  • harmony_types · array · optionnel
    Harmony types to include: 'complementary', 'analogous', 'triadic', 'split_complementary', 'tetradic', or 'hay_contrast' (D.R. Hay's 1838 documented contrast pairing, distinct from the geometric types -- see tool description).

  Exemple d'appel

  {"name": "colour_harmonies", "arguments": {"hex": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_hooks≈ 300 tokens

  Generate a hook sentence, three-sentence story, tweet, image prompt, and follow-up questions for any hex colour. Backed by the nearest archive colour's cultural provenance. Tunable by audience (general public, designers, historians, children) and tone (dinner party, academic, social media, brand copy). Use to make archive colours shareable, to generate content, or to power a public-facing colour chat experience.

  Paramètres, retour & exemple (3)

  Paramètres

  • hex · string · requis
    Hex colour e.g. '#154F20'
  • tone · string · optionnel
    Desired tone e.g. 'dinner party', 'academic', 'social media', 'brand copy'
  • audience · string · optionnel
    Target audience e.g. 'general public', 'interior designers', 'children'

  Exemple d'appel

  {"name": "colour_hooks", "arguments": {"hex": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_match_paint≈ 199 tokens

  Find the nearest named colour in commercial paint systems including Farrow and Ball and Little Greene.

  Paramètres, retour & exemple (3)

  Paramètres

  • n · integer · optionnel
    Number of matches (default 3)
  • brand · string · optionnel
    Optional brand filter: 'farrow' or 'little_greene'
  • hex_val · string · requis
    Hex value e.g. '#003153'

  Exemple d'appel

  {"name": "colour_match_paint", "arguments": {"hex_val": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_metrics≈ 249 tokens

  Returns numeric metrics derived from a single display colour: an estimated light reflectance value (LRV) and band, relative luminance, CIELAB lightness, chroma and hue angle, and Bradford corresponding colours under two standard illuminants. It also lists what a hex cannot support, such as thermal performance or a measured LRV. This is one component of colour_passport. Use colour_passport for a general colour profile; use this only when the user explicitly wants isolated numeric values.

  Paramètres, retour & exemple (1)

  Paramètres

  • hex_val · string · requis
    Hex value e.g. '#8B4513'

  Exemple d'appel

  {"name": "colour_metrics", "arguments": {"hex_val": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_mix≈ 278 tokens

  Simulate perceptually modelled subtractive mixing of two colours in CIE Lab space (not RGB screen blending). Returns the resulting mixed hex value and its nearest archive match with cultural context. Uses CIE Lab subtractive model for perceptual accuracy. Example: mixing Prussian Blue and Yellow Ochre gives a muted green — the tool identifies which archive colour that green most closely matches.

  Paramètres, retour & exemple (3)

  Paramètres

  • hex_a · string · requis
    First colour hex e.g. '#003366'
  • hex_b · string · requis
    Second colour hex e.g. '#C8A600'
  • ratio · number · optionnel
    Mix ratio 0.0-1.0 where 0.5 is equal parts (default 0.5)

  Exemple d'appel

  {"name": "colour_mix", "arguments": {"hex_a": "texte", "hex_b": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_namer≈ 290 tokens

  Generate memorable, archive-verified colour names for any hex value. Choose from naming styles: geographical, poetic, material, literary, botanical, industrial, or mixed. Every name is grounded in a real archive source. The core of the Shopify product naming use case.

  Paramètres, retour & exemple (5)

  Paramètres

  • hex · string · requis
    Hex colour to name e.g. #8B4A2A
  • style · string · optionnel
    geographical | poetic | material | literary | botanical | industrial | mixed
  • market · string · optionnel
    Target market e.g. UK luxury
  • n_names · integer · optionnel
    Number of name options (default 5)
  • product_type · string · optionnel
    Product type e.g. candle, paint, leather bag

  Exemple d'appel

  {"name": "colour_namer", "arguments": {"hex": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_passport≈ 460 tokens

  Canonical single-call colour truth object. Returns everything known about a hex value: colour science (Lab, LCh, hue, chroma, depth, temperature, LRV), archive anchor with dE2000, claim_strength, do_not_say and evidence grade, hex provenance (status, confidence, spectrophotometric flag), physics (illuminant behaviour, gamut, print risk), and cultural reading (colour family, warnings, positives). Use this as the foundation call when you need the complete picture. Every other tool is built on this data. Replaces chaining colour_dna + archive_provenance + colour_cultural_risk + colour_metrics separately. Examples: '#31559B' (anchors to Henry VIII Manuscript Blue Initials), '#8B1A1A' (Penny Post Sealing Wax Dark Red), '#D4AF37' (Sutton Hoo Great Gold Buckle).

  Paramètres, retour & exemple (5)

  Paramètres

  • hex · string · optionnel
    Single hex colour e.g. #31559B
  • hexes · array · optionnel
    Multiple hex colours for batch lookup e.g. ['#31559B', '#8B1A1A']. Max 20.
  • n_archive · integer · optionnel
    Number of archive matches to return (default 3)
  • include_physics · boolean · optionnel
    Include illuminant behaviour and gamut data (default true)
  • include_cultural · boolean · optionnel
    Include cultural risk and associations (default true)

  Exemple d'appel

  {"name": "colour_passport", "arguments": {"hex": "texte", "hexes": [], "n_archive": 1, "include_physics": true, "include_cultural": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_passports≈ 320 tokens

  Batch version of colour_passport. Submit up to 20 hex values in one call. Returns a full Colour Passport for each unique hex: colour science, archive anchor, evidence grade, do_not_say constraints, hex provenance, accessibility, and physics. Deduplicates hex values automatically. Use for multi-colour workflows, Figma palette analysis, or any case where calling colour_passport separately for each colour would be slow.

  Paramètres, retour & exemple (4)

  Paramètres

  • hexes · array · requis
    List of hex colours e.g. ['#31559B', '#8B1A1A']
  • n_archive · integer · optionnel
    Number of archive matches per colour (default 3)
  • include_physics · boolean · optionnel
    Include illuminant behaviour and gamut data (default true)
  • include_cultural · boolean · optionnel
    Include cultural associations (default false)

  Exemple d'appel

  {"name": "colour_passports", "arguments": {"hexes": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_relationships≈ 508 tokens

  What is this archive record connected to, and why? One-hop lookup over Colour Memory's stored relationship graph -- today populated for PigmentLineage, whose 348 design_combination nodes are Wada's 1933 Dictionary of Color Combinations plates. Returns edges in separate blocks by relationship_class so a caller can never mistake a computed colour distance for something a historical source actually said: SOURCE_ASSERTED (the source itself states the relationship, e.g. 'this colour was assigned to numbered combination 176') versus DETERMINISTIC_STRUCTURAL (a mechanical fact about the source object, e.g. 'printed on this plate'). Every edge carries its own 'does_not_mean' caveat inline -- e.g. membership in the same Wada combination does not assert that any specific pair within it was individually intended as a pairing. Not every record_id has relationships yet; an empty result is a true negative, not an error. Get record_id values from archive_search or colour_card.

  Paramètres, retour & exemple (3)

  Paramètres

  • record_id · string · requis
    Stable record id, e.g. from archive_search or colour_card.
  • include_computed · boolean · optionnel
    Include computed (not source-asserted) relationships where available. Default true.
  • include_unresolved · boolean · optionnel
    Include same-name candidates across sources -- the cheapest, easiest-to-misread-as-evidence edge in the system. Default false.

  Exemple d'appel

  {"name": "colour_relationships", "arguments": {"record_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"label": "texte", "record_id": "texte", "structural": {}, "source_asserted": {}}}

• colour_slugs≈ 190 tokens

  Return every developer token format for a hex value: CSS variable, kebab-case, camelCase, PascalCase, Tailwind class, TypeScript const, SCSS variable. Archive-grounded name source with dE2000 distance.

  Paramètres, retour & exemple (2)

  Paramètres

  • hex · string · requis
    Hex value e.g. #D4A829
  • archive · string · optionnel
    Optional archive filter

  Exemple d'appel

  {"name": "colour_slugs", "arguments": {"hex": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_story≈ 252 tokens

  Given a hex value, returns a rich narrative about that colour's cultural journey — where it has appeared in history, what it has meant to different civilisations, and what archive names it carries. Essential for image generation prompts, brand storytelling, and creative briefs. Example: '#DC143C' returns the story of crimson from Byzantine imperial courts through Tudor England to modern sport.

  Paramètres, retour & exemple (2)

  Paramètres

  • hex · string · requis
    Hex value e.g. '#DC143C'
  • n_archives · integer · optionnel
    Number of archive sources to draw from (default 5)

  Exemple d'appel

  {"name": "colour_story", "arguments": {"hex": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_strategy≈ 590 tokens

  Single-call commercial colour strategy report. Combines archive grounding, verdict, brand fit, market risk, category cliche check, material behaviour, copy hooks, and usage rules. Input: hex + brand_context (category, positioning, audience, channels) + constraints (avoid, must_work_on) + markets + medium. Output: verdict, strategy summary, archive anchor, commercial signal, category cliche risk level, market reading per market, material notes, usage rules (primary use, secondary use, avoid, pair_with), copy hooks (one_liner, social, brand_rationale), and alternatives. Examples: luxury fragrance brand UK/France/Japan, heritage interior specification, premium ecommerce packaging, SaaS brand identity.

  Paramètres, retour & exemple (5)

  Paramètres

  • hex · string · requis
    Hex colour to evaluate e.g. '#4A2A50'
  • medium · string · optionnel
    Primary medium e.g. 'packaging', 'interior', 'digital'
  • markets · array · optionnel
    Target markets e.g. ['UK', 'France', 'Japan']
  • constraints · object · optionnel
    Constraints object
  • brand_context · object · optionnel
    Brand context object

  Exemple d'appel

  {"name": "colour_strategy", "arguments": {"hex": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_timeline≈ 293 tokens

  Given a concept or colour name, traces its documented appearances across cultures and centuries in chronological order. Returns a dated sequence of archive entries showing when and where the colour appeared, with primary sources. Use for historical research, provenance chains, and understanding why a colour carries the cultural weight it does. Example: 'indigo' traces from ancient Indian trade routes through Roman imports to Tudor sumptuary law to synthetic aniline displacement in 1897.

  Paramètres, retour & exemple (2)

  Paramètres

  • n · integer · optionnel
    Number of timeline entries to return (default 10, max 20)
  • concept · string · requis
    Colour name or concept to trace e.g. indigo, imperial purple, mourning black

  Exemple d'appel

  {"name": "colour_timeline", "arguments": {"concept": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_variants≈ 277 tokens

  For any named archive colour, return historical variants, lighter and darker versions with archive matches, and cultural siblings. Essential for designers exploring around a colour. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (1)

  Paramètres

  • name · string · requis
    Named archive colour e.g. Bourton Honey

  Exemple d'appel

  {"name": "colour_variants", "arguments": {"name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• colour_verdict≈ 376 tokens

  Evaluate a hex colour for a specific use case, market, and medium. Returns a decisive verdict: use_with_confidence, use_with_caution, or avoid. Includes strengths, risks, avoid-if scenarios, and better alternatives where needed. Backed by CIEDE2000 archive matching and Claude cultural intelligence. Examples: 'luxury hotel brand in Japan', 'ecommerce CTA button UK', 'heritage interior lime plaster wall', 'premium packaging Middle East'.

  Paramètres, retour & exemple (5)

  Paramètres

  • hex · string · requis
    Hex colour to evaluate e.g. '#31559B'
  • medium · string · optionnel
    Application medium e.g. 'digital', 'interior', 'print', 'fashion', 'packaging'
  • markets · array · optionnel
    Target markets e.g. ['UK', 'Japan', 'UAE']
  • audience · string · optionnel
    Optional: target audience e.g. 'high net worth travellers', 'young professionals'
  • use_case · string · requis
    What the colour will be used for e.g. 'luxury hotel brand', 'heritage interior wall'

  Exemple d'appel

  {"name": "colour_verdict", "arguments": {"hex": "texte", "use_case": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• design_session≈ 592 tokens

  One-call compound tool. Submit a concept, medium, audience, and constraints — receive a complete design package: historically grounded palette, cultural narrative, commercial paint matches, WCAG accessibility check, illuminant behaviour, and a ready-made image generation prompt. Replaces chaining query_conceptual + palette_from_concept + colour_story + match_paint_system + accessibility_check + get_colour_metrics. Use when an AI agent or user needs a complete, deployable colour direction in a single call. Not for iterative refinement — use individual tools for that. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (7)

  Paramètres

  • avoid · array · optionnel
    Archive names or colour terms to exclude e.g. ['neon', 'ScreenDigital']
  • medium · string · optionnel
    Application context e.g. 'interior', 'brand identity', 'fashion', 'digital', 'print'
  • concept · string · requis
    Cultural theme, mood, or brief e.g. 'Victorian mourning', 'Ottoman court', 'Scandinavian minimal'
  • n_colours · integer · optionnel
    Palette size (default 5, max 8)
  • include_prompt · boolean · optionnel
    Include image generation prompt (default true)
  • include_accessibility · boolean · optionnel
    Include WCAG contrast check (default true)
  • include_paint_matches · boolean · optionnel
    Include commercial paint matches (default true)

  Exemple d'appel

  {"name": "design_session", "arguments": {"concept": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ecommerce_copy≈ 417 tokens

  Generate complete ecommerce product copy for any colour. Input: hex + product type + tone + channel. Output: colour name, product title, short description, long description, SEO title, meta description, alt text, Instagram caption, and cross-sell suggestion. Every piece of copy is grounded in archive provenance -- never generic AI colour copy. The colour name comes from the nearest archive match, not invented. Examples: velvet cushion in Murex Luxury, ceramic vase in Woad Vat Blue, linen throw in Standlake Silt. Directly useful for Shopify, WooCommerce, and editorial product pages.

  Paramètres, retour & exemple (5)

  Paramètres

  • hex · string · requis
    Hex colour of the product e.g. '#4A2A50'
  • tone · string · optionnel
    Copy tone e.g. 'premium but not pompous', 'warm and accessible', 'heritage and serious'
  • channel · string · optionnel
    Sales channel e.g. 'shopify', 'etsy', 'instagram', 'editorial'
  • brand_name · string · optionnel
    Optional brand name to include in copy
  • product_type · string · requis
    Product type e.g. 'velvet cushion', 'ceramic vase', 'linen throw', 'candle'

  Exemple d'appel

  {"name": "ecommerce_copy", "arguments": {"hex": "texte", "product_type": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ecommerce_namer≈ 364 tokens

  Generate archive-grounded colour names for up to 40 product SKUs. Input: list of hex values, product category, brand name, naming style. Output: for each hex -- archive name, source citation, one-line product description, dE2000 match distance, match quality, and confidence score. Every name is archive-sourced, not invented. Each carries a primary source citation that can be defended to buyers, press, and brand teams. Use for paint ranges, candle collections, fashion lines, homeware, cosmetics. Style options: geographical, poetic, material, literary, mixed.

  Paramètres, retour & exemple (5)

  Paramètres

  • hexes · array · requis
    List of hex values e.g. ['#D4A829', '#1A5C6E']
  • style · string · optionnel
    geographical | poetic | material | literary | mixed (default)
  • max_dE · number · optionnel
    Max dE2000 distance to accept (default 25)
  • brand_name · string · optionnel
    Brand name for context
  • product_category · string · optionnel
    e.g. 'paint', 'candle', 'fashion', 'homeware'

  Exemple d'appel

  {"name": "ecommerce_namer", "arguments": {"hexes": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• extract_image_colours≈ 434 tokens

  Extract dominant colours from a photograph using Colour Memory's proprietary k-means++ algorithm. Requires either a public image_url, or an image_id. If you only have a raw uploaded file with no public URL (e.g. a local file path or a ChatGPT file attachment without a usable download_url), call ingest_image first to get an image_id, then pass that image_id here. Returns hex values with proportional weights. Optionally matches colours against the archive with style_context for coherent cultural naming. Use this before image_brief when you have an uploaded photograph.

  Paramètres, retour & exemple (7)

  Paramètres

  • k · integer · optionnel
    Number of colours to extract (3-12, default 6)
  • image · object · optionnel
    Image file attachment from ChatGPT
  • analyse · boolean · optionnel
    If true, match colours against archive and return names
  • image_id · string · optionnel
    Ephemeral image_id returned by ingest_image. Use this if you only have a local file path or raw file attachment with no public URL.
  • image_url · string · optionnel
    Public URL of image
  • grey_card_hex · string · optionnel
    Hex from a grey/white card for white balance
  • style_context · string · optionnel
    e.g. English cottage garden, Victorian, Japanese

  Exemple d'appel

  {"name": "extract_image_colours", "arguments": {"k": 1, "image": {}, "analyse": true, "image_id": "texte", "image_url": "texte", "grey_card_hex": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• historical_colour_query≈ 598 tokens

  Ask a question about how historical colour authorities actually reasoned, and get evidence with provenance rather than a summary. Covers seven validated source builds -- Jennings (paint recipes, 1902), Bradley (rotating-disc apparatus, 1895), Vanderpoel (quantified object analyses, 1902), Beaumont (woven colour relationships), Hay (harmonic proportional powers, 1838), Guichard (measured spatial extents, 1880) and Hokusai (subject-conditioned colour application, 1848). Each answer names its source, its locator and what that kind of evidence CANNOT support. Use it for questions like 'how do I paint a leaf', 'what did Bradley's disc proportions measure', 'what's the difference between making a colour and applying it', or to check a claim someone has attributed to one of these authors. Crucially, these sources' numbers are NOT interchangeable: a recipe part, a disc share, an object percentage, a proportional power and a measured extent answer different questions, and the response says so explicitly rather than averaging them.

  Paramètres, retour & exemple (5)

  Paramètres

  • mode · string · optionnel · user | evidence
    'user' (default) returns an evidence-led answer packet with structured values retained. 'evidence' additionally returns the complete underlying records.
  • query · string · requis
    Plain-English historical colour question.
  • sources · array · optionnel
    Optional restriction to named sources.
  • max_results · integer · optionnel
    Upper bound on evidence items (default 12).
  • high_confidence_only · boolean · optionnel
    Only high-confidence records.

  Exemple d'appel

  {"name": "historical_colour_query", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"answer": {}, "evidence": [], "do_not_say": [], "incomparabilities": [], "premise_correction": {}}}

• house_specify≈ 1415 tokens

  Generate a complete multi-room house colour scheme from a single archive. Where the retrieved evidence supports it, rooms are grouped by documented provenance (same object, same pattern colourway, same source citation, same designer, same period+institution); where it does not, they are grouped by perceptual similarity and the response says so -- grouping_basis reports which, and provenance_credit reports how many delivered colours are individually evidenced versus documented as a GROUP (often zero). Every colour is a real archive record either way. Each room gets a full colour card set (dominant/secondary/joinery/textile/accent roles) with paint matches, LRV, illuminant behaviour, and WCAG data. A documentary grouping states exactly which documented fact ties its colours together (e.g. 'documented on the same Fitzwilliam Museum record for the Artichoke hanging, accession T.1-1979') and its weighted grouping_strength score -- historical claims are templated only from fields the archive record actually states; room/surface assignment is disclosed as editorial, never as historical fact. Orientation (north/south/east/west) is recorded as room context and surfaced in each room's light_context; in the current model it does not alter palette selection. Example: concept='Arts and Crafts movement family house', archive='ArtsAndCrafts', rooms=[{label:'Entrance Hall', room_type:'hallway', orientation:'north'}, {label:'Living Room', room_type:'living', orientation:'south'}]. Use interior_specify instead for a single room without cross-room grouping. The response includes house_ref -- pass that (not the full response) to palette_pdf's house_ref input to render the flagship document; the full response is often 60-100KB+, too large to safely resend as another tool call's input. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (11)

  Paramètres

  • avoid · array · optionnel
    Terms to exclude from retrieval.
  • rooms · array · requis
    One entry per room, e.g. [{label:'Entrance Hall', room_type:'hallway', orientation:'north'}]
  • archive · string · requis
    Single archive to draw every room's colours from, e.g. 'ArtsAndCrafts'. Required -- invalid names return a clear error listing valid archives.
  • concept · string · requis
    House-level concept or brief, e.g. 'Arts and Crafts movement family house'
  • output_format · string · optionnel · standard | scene_brief
    'scene_brief' adds a Historical Scene Colour Brief for film and image work: per colour its place, date, observer, timing, source and do-not-claim lines, then DOCUMENTED VISUAL CONSTRAINTS, NEGATIVE / DO-NOT-INVENT constraints and a CREATIVE RECONSTRUCTION BOUNDARY. Evidence only; nothing is invented.
  • guidance_level · string · optionnel · client | decorator
    Who the guidance notes are written for. 'client' (default) for a homeowner; 'decorator' for a trade reader. The specification decisions are identical either way -- only the wording differs.
  • narrative_mode · string · optionnel
    Default 'evidence_only'.
  • colours_per_room · integer · optionnel
    Default 5.
  • shared_house_colours · integer · optionnel
    Default 2.
  • minimum_claim_strength · string · optionnel
    Evidence-grade floor, default 'B'. Explicitly supplied: a hard admission filter, never relaxed -- too few qualifying records fails closed with a per-grade availability map (ARCHIVE_EVIDENCE_POOL_DEPLETED). Left at the implicit default: if the archive's best relevant records sit below it, the design-admissibility floor is relaxed to the archive's best achievable grade and disclosed in the response's evidence_floor block. Colours always keep their true evidence grade either way -- claims are never upgraded.
  • strict_semantic_colour · boolean · optionnel
    Default true -- excludes entries whose quoted colour language contradicts their stored hex.

  Exemple d'appel

  {"name": "house_specify", "arguments": {"rooms": [], "archive": "texte", "concept": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• image_brief≈ 531 tokens

  Compound endpoint: one image in, full creative brief out. Extracts dominant colours, matches them to the Colour Memory archive with coherent cultural naming, understands the scene, identifies the style period, suggests product directions by category (textiles, interiors, fashion), generates an image generation prompt, and returns a swatch URL. Use instead of chaining palette_extract + palette_analyse + agent_brief separately. Pass style_context for coherent archive matching e.g. 'English cottage garden', 'Victorian', 'MarsColour'. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (8)

  Paramètres

  • k · integer · optionnel
    Number of colours to extract (3-12, default 6)
  • model · string · optionnel
    Image model: midjourney | flux | dalle | stable_diffusion (default midjourney)
  • archive · string · optionnel
    Explicit archive name override e.g. 'MarsColour', 'Japan'
  • image_url · string · optionnel
    Public URL of the image
  • image_base64 · string · optionnel
    Base64-encoded image data
  • product_type · string · optionnel
    Product focus e.g. 'tea towel', 'wallpaper', 'ceramic', 'textile'
  • grey_card_hex · string · optionnel
    Hex value from a grey/white card for white balance correction
  • style_context · string · optionnel
    Plain English style e.g. 'English cottage garden', 'Victorian', 'Japanese', 'MarsColour'. Restricts archive matching to coherent cultural set.

  Exemple d'appel

  {"name": "image_brief", "arguments": {"k": 1, "model": "texte", "archive": "texte", "image_url": "texte", "image_base64": "texte", "product_type": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• image_palette≈ 448 tokens

  Upload an image (base64 encoded) and extract its dominant colour palette, with each colour matched to its nearest named archive entry with full cultural provenance. Uses K-means++ extraction; sRGB pixels are read as D65 CIELAB for matching. Returns up to 5 dominant colours, each with archive name, cultural story, nearest RAL standard, and WCAG accessibility data. Works for product photography, interior photos, artwork, brand assets, and mood boards. The image is never stored — processed in memory only. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (4)

  Paramètres

  • archive · string · optionnel
    Optional: restrict archive matching to a specific archive
  • n_colours · integer · optionnel
    Number of dominant colours to extract (default 5, max 5)
  • media_type · string · optionnel
    Image MIME type e.g. 'image/jpeg'
  • image_base64 · string · requis
    Base64 encoded image (JPEG, PNG, WebP)

  Exemple d'appel

  {"name": "image_palette", "arguments": {"image_base64": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• image_personal≈ 400 tokens

  Upload a portrait photo and receive a full personal colour analysis. Determines your seasonal type (Spring, Summer, Autumn, or Winter), colour depth (light, medium, or deep), and undertone (warm, cool, or neutral). Returns a curated palette of archive colours that genuinely suit you — each with full historical provenance and cultural context — plus colours to avoid. Uses Claude Vision for skin, hair, and eye analysis, then matches to the archive by CIEDE2000 perceptual distance. The photo is never stored. Example: a Deep Winter might wear Ottoman Carbon Ink while a True Spring suits Kogi Mango.

  Paramètres, retour & exemple (4)

  Paramètres

  • name · string · optionnel
    Optional: person's name for the report e.g. 'Sarah'
  • image_url · string · optionnel
    URL of a portrait photo hosted online. Easier than base64 for MCP use. Either image_url or image_base64 required.
  • media_type · string · optionnel
    Image MIME type e.g. 'image/jpeg'
  • image_base64 · string · optionnel
    Base64 encoded portrait photo (JPEG or PNG). Face should be clearly visible in natural light. Either image_base64 or image_url required.

  Exemple d'appel

  {"name": "image_personal", "arguments": {"name": "texte", "image_url": "texte", "media_type": "texte", "image_base64": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• index_resonance≈ 369 tokens

  Colour Memory's proprietary semantic metric. Score how tightly the material origin of a colour aligns with its social consequence. 1.00 = material and consequence are indistinguishable (blood as prognosis, ash as finality). 0.80 = institution mediates the colour (paint as deterrence, flag as authority). 0.50 = symbolic or associative only. Input: list of colour entries with name, hex, archive, source, notes. Output: resonance score, material origin, social function, alignment reason, confidence. Use for investigative reports, forensic briefs, museum content, editorial PDFs. This is the metric that separates Colour Memory from palette generators.

  Paramètres, retour & exemple (2)

  Paramètres

  • entries · array · requis
    List of colour entries to score for resonance
  • score_basis · string · optionnel
    Scoring basis (default: material_origin_to_social_consequence)

  Exemple d'appel

  {"name": "index_resonance", "arguments": {"entries": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ingest_image≈ 230 tokens

  Upload an image to Colour Memory for ephemeral processing. Returns image_id valid 5 minutes. Pass image_id to palette_extract or image_brief. Use for any image over 50 KB.

  Paramètres, retour & exemple (3)

  Paramètres

  • image · object · optionnel
    MCP file reference {download_url, mime_type, file_name}
  • source_url · string · optionnel
    HTTPS URL of the image
  • image_base64 · string · optionnel
    Base64-encoded image data. Use this for locally uploaded files with no public URL. No size limit here (unlike palette_extract's image_base64).

  Exemple d'appel

  {"name": "ingest_image", "arguments": {"image": {}, "source_url": "texte", "image_base64": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• interior_specify≈ 1296 tokens

  Generate a complete interior colour specification from a concept or brief. Input a room concept, type, and style — receive a professionally structured colour scheme with 60/30/10 surface assignments, archive colour names with full cultural provenance, Farrow and Ball and Little Greene paint matches, three-illuminant light behaviour (D65 daylight, F11 atrium, Illuminant A incandescent), WCAG accessibility for digital use, and a written cultural rationale explaining why each colour belongs in this room. Examples: 'bold maximalist living room', 'calm Scandi bedroom', 'Victorian study', 'coastal kitchen', 'gallery hallway'. Pass `archive` to lock the whole scheme to one named archive (e.g. 'ArtsAndCrafts', 'GeorgianPleasures') -- every returned colour will belong to it, or you get a clear error listing valid archive names rather than a silent unrestricted search. Use /interior-specification/pdf for a downloadable branded PDF version. Use house_specify instead for a multi-room scheme with cross-room provenance grouping. This is the tool that replaces a colour consultation. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (9)

  Paramètres

  • avoid · array · optionnel
    Colours, pigments or topics to exclude e.g. ['arsenic green']. Applied before selection.
  • style · string · optionnel
    Style direction e.g. 'heritage', 'contemporary', 'maximalist', 'minimal', 'scandi', 'industrial', 'coastal'
  • archive · string · optionnel
    Optional: restrict the candidate pool to this single archive before scoring, e.g. 'ArtsAndCrafts' or 'GeorgianPleasures'. Invalid names return a clear error listing valid archives rather than silently searching everything. Omit for unrestricted cross-archive search (default, unchanged behaviour).
  • concept · string · requis
    Room concept or brief e.g. 'bold maximalist living room' or 'calm Scandi bedroom'
  • n_colours · integer · optionnel
    Number of colours in scheme (default 5, max 7)
  • role_plan · array · optionnel
    Optional: the room's spatial hierarchy, decided BEFORE colours are retrieved, so retrieval can be asked for candidates that suit a named job on a named surface. The role vocabulary is open -- field, architectural, ground, joinery, material, textile, accent and signal are all reasonable, and a room may need three of them or six. Omit to let the endpoint decide the hierarchy itself (unchanged behaviour).
  • room_type · string · optionnel
    Room type e.g. 'living', 'bedroom', 'kitchen', 'study', 'bathroom', 'hallway', 'dining'
  • orientation · string · optionnel
    Room orientation e.g. 'north', 'south', 'east', 'west' — affects light advice
  • output_format · string · optionnel · standard | scene_brief
    'scene_brief' adds a Historical Scene Colour Brief for film and image work: per colour its place, date, observer, timing, source and do-not-claim lines, then DOCUMENTED VISUAL CONSTRAINTS, NEGATIVE / DO-NOT-INVENT constraints and a CREATIVE RECONSTRUCTION BOUNDARY. Evidence only; nothing is invented.

  Exemple d'appel

  {"name": "interior_specify", "arguments": {"concept": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• meta_capabilities≈ 163 tokens

  Return a live inventory of all active endpoints and MCP tools. Use this first to discover what the API can do before making calls. Returns tool count, endpoint list, MCP-exposed tools, and usage notes. Deterministic -- no LLM cost.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "meta_capabilities", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_analyse≈ 400 tokens

  Analyse a palette of hex colours against the Colour Memory archive. For each colour returns the nearest named archive entry with cultural name, source, claim_strength (A-E), do_not_say guardrails, and alternatives when confidence is low. Palette-level deduplication ensures no two colours map to the same archive entry. Use after extracting colours from a photo or generating a palette. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (3)

  Paramètres

  • n · integer · optionnel
    Max alternatives per colour when confidence is low (1-3, default 1)
  • archive · string · optionnel
    Optional: restrict to one archive e.g. China, Pigment, ArtsAndCrafts
  • colours · array · requis
    Array of colour objects

  Exemple d'appel

  {"name": "palette_analyse", "arguments": {"colours": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_audit≈ 370 tokens

  Full palette quality audit. Scores on accessibility, cultural risk, tonal balance, colour diversity, and archive naming strength. Returns overall score 0-100, grade, and prioritised fix list. Enterprise quality gate -- use before shipping any palette. Deterministic, no LLM cost. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (4)

  Paramètres

  • market · string · optionnel
    Target market
  • medium · string · optionnel
    digital | print | both
  • palette · array · requis
    Hex values to audit
  • use_case · string · optionnel
    Use case context

  Exemple d'appel

  {"name": "palette_audit", "arguments": {"palette": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_compare≈ 362 tokens

  Deep perceptual, cultural, and commercial comparison between two palettes. Returns timelessness scores, commercial strength, cultural depth, emotional difference, and a winner verdict for the stated use case. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (4)

  Paramètres

  • markets · array · optionnel
    Target markets
  • use_case · string · optionnel
    Context for comparison e.g. luxury packaging
  • palette_a · array · requis
    First palette hex values
  • palette_b · array · requis
    Second palette hex values

  Exemple d'appel

  {"name": "palette_compare", "arguments": {"palette_a": [], "palette_b": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_concept≈ 443 tokens

  Generate a historically grounded colour palette from a cultural concept or theme. Returns 4-6 coordinated archive colours with hex values, proportions, and provenance. Examples: 'Victorian mourning', 'Ottoman court', 'Japanese wabi-sabi', 'Scandinavian winter', 'West African kente', 'Renaissance Florence'. Every colour returned is sourced from the archive with documented history. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (4)

  Paramètres

  • avoid · array · optionnel
    Colours, pigments or topics to exclude e.g. ['arsenic green']. Applied before selection.
  • concept · string · requis
    Cultural theme or historical period e.g. 'Victorian mourning' or 'Ottoman court'
  • n_colours · integer · optionnel
    Number of colours to return (default 5, max 8)
  • include_neutrals · boolean · optionnel
    Include neutral/background colours

  Exemple d'appel

  {"name": "palette_concept", "arguments": {"concept": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_export≈ 253 tokens

  Export a palette to CSS custom properties, Figma design tokens, Tailwind config, ASE hex list, or JSON. Each colour is automatically named from the archive. Embeds Colour Memory directly into design workflows.

  Paramètres, retour & exemple (4)

  Paramètres

  • names · array · optionnel
    Optional custom names
  • format · string · optionnel
    css | figma | ase_hex | tailwind | json
  • prefix · string · optionnel
    Token prefix e.g. cm, brand (default: cm)
  • palette · array · requis
    Hex values to export

  Exemple d'appel

  {"name": "palette_export", "arguments": {"palette": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_extract≈ 543 tokens

  Extract dominant colours from an image using k-means++ clustering. Accepts a public image URL or base64-encoded image. Returns hex values with proportional weights sorted by luminance. Optionally runs palette_analyse on the results. Use this instead of image_palette when you need hex values with proportions for palette_analyse or palette_swatch. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (8)

  Paramètres

  • k · integer · optionnel
    Number of colours to extract (3-12, default 6)
  • analyse · boolean · optionnel
    If true, also run palette_analyse on the extracted colours and return archive names
  • archive · string · optionnel
    Explicit single archive name to restrict matching to e.g. 'MarsColour', 'Japan', 'Victorian'.
  • image_id · string · optionnel
    Ephemeral image_id from ingest_image (preferred for images over 50 KB)
  • image_url · string · optionnel
    Public URL of the image to extract colours from
  • image_base64 · string · optionnel
    Base64-encoded image data (small images only, under 50 KB)
  • grey_card_hex · string · optionnel
    Hex value sampled from a grey or white card in the image for white balance correction e.g. #C8C8C8
  • style_context · string · optionnel
    Plain English style description that restricts archive matching to a coherent set e.g. 'English cottage garden', 'Victorian', 'Japanese', 'MarsColour', 'Arts and Crafts'. Prevents palette colours from being named across unrelated archives.

  Exemple d'appel

  {"name": "palette_extract", "arguments": {"k": 1, "analyse": true, "archive": "texte", "image_id": "texte", "image_url": "texte", "image_base64": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_finalize≈ 529 tokens

  Package a palette YOU HAVE ALREADY CHOSEN into a professional, visible, downloadable deliverable. Call this ONCE, after you have decided the final colours for the customer -- it verifies and packages your decision and returns the palette image plus PNG, SVG, PDF, ASE, JSON and CSS. It does not search, select, replace or improve anything: the colours you send are the colours that come back, in your order. Send every final colour with its name, and mark a colour source-backed only if it really is a Colour Memory archive record -- anything unverified is presented as your recommendation, which is the honest description of it.

  Paramètres, retour & exemple (5)

  Paramètres

  • brief · string · optionnel
    The customer's request, in their words.
  • notes · array · optionnel
    Short usage guidance, in your words.
  • title · string · optionnel
    What you are calling this palette.
  • colours · array · requis
    The final palette, in the order you want it shown.
  • source_anchors · array · optionnel
    Archive records that informed the palette but are not in it. Give the record's name so it can be verified.

  Exemple d'appel

  {"name": "palette_finalize", "arguments": {"colours": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_generate≈ 531 tokens

  Send a palette of up to 12 slots, locking some with hex values and leaving others empty. Empty slots are filled with the nearest CIEDE2000 archive match, interpolated from the locked anchors. Optional archive filter restricts fills to one archive. Returns full citation — name, archive, primary source, colour notes — for every filled slot. Example: lock a client's existing wall colour and fill a 5-colour scheme from Oxfordshire. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (3)

  Paramètres

  • size · integer · optionnel
    Total CURATED palette size 2-12 (default 5). This is the designed-palette ceiling, not a product limit on how many colours exist: for a large colour COLLECTION, page archive_search instead.
  • slots · array · requis
    List of palette slots. Each has index (0-11), optional hex, and locked flag.
  • archive · string · optionnel
    Optional: restrict fills to one archive e.g. 'Oxfordshire', 'Shakespeare', 'Japan'

  Exemple d'appel

  {"name": "palette_generate", "arguments": {"slots": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_gradient≈ 558 tokens

  Generate a perceptually smooth gradient between 2-5 archive anchor colours. Each interpolated stop snaps to the nearest real archive colour by CIEDE2000. Anchor stops are kept true to their source. Choose linear (physically accurate Lab interpolation) or chroma_preserved (LCh interpolation, short-arc hue, avoids desaturated midpoints). Returns stop array, CSS linear-gradient string, or SVG swatch bar. Use for design briefs, colour journey visualisations, and gradient systems. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (6)

  Paramètres

  • path · string · optionnel · linear | chroma_preserved
    linear: straight Lab lerp (may have neutral midpoint). chroma_preserved: LCh short-arc, saturation maintained.
  • steps · integer · optionnel
    Total stops including anchors (default 7, max 20)
  • anchors · array · requis
    2-5 hex values (#RRGGBB) or exact archive colour names
  • archive · string · optionnel
    Restrict snapping to this archive name e.g. Victorian
  • output_format · string · optionnel · stops | css | svg
    stops: array of colour objects. css: linear-gradient string. svg: swatch bar.
  • snap_to_archive · boolean · optionnel
    Snap each stop to nearest archive colour (default true)

  Exemple d'appel

  {"name": "palette_gradient", "arguments": {"anchors": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_heritage≈ 394 tokens

  Given a legacy palette, generate an archive-grounded premium support system. For each existing colour: identifies its historical archive anchor, names it, and scores its provenance confidence. Detects palette gaps and fills them from the archive. Returns full palette with roles, confidence scores, CSS tokens, and production notes. Every addition has a named historical origin. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (5)

  Paramètres

  • market · string · optionnel
    Target market
  • context · string · optionnel
    Brand context
  • palette · array · requis
    Existing hex values
  • brand_name · string · optionnel
    Brand name for CSS tokens
  • n_additions · integer · optionnel
    Archive colours to add (default 3)

  Exemple d'appel

  {"name": "palette_heritage", "arguments": {"palette": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_iterate≈ 439 tokens

  Refine an existing palette using natural language feedback. Submit your current palette and feedback such as more melancholic, too corporate add warmth, or better for Gen Z luxury. Returns a refined palette with archive grounding and change rationale. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (6)

  Paramètres

  • markets · array · optionnel
    Target markets
  • palette · array · requis
    Current hex palette to refine
  • feedback · string · requis
    Natural language refinement e.g. more melancholic
  • use_case · string · optionnel
    Use case context e.g. luxury homewares
  • direction · string · optionnel
    Alias for feedback — natural language direction e.g. more dangerous, more historical, warmer
  • n_results · integer · optionnel
    Number of variants to return (default 1)

  Exemple d'appel

  {"name": "palette_iterate", "arguments": {"palette": [], "feedback": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_light_dark≈ 312 tokens

  Generate light-mode and dark-mode role maps from a palette. Analyses LRV, assigns background/surface/text/accent roles for each mode, checks body text contrast safety, and flags missing neutrals. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (2)

  Paramètres

  • palette · array · requis
    Array of hex values
  • use_case · string · optionnel
    Use case context e.g. UI, dashboard, report

  Exemple d'appel

  {"name": "palette_light_dark", "arguments": {"palette": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_pdf≈ 2217 tokens

  Generate a premium branded PDF specification sheet from a palette of archive entries. Returns a downloadable PDF with full-bleed colour panels, archive names, provenance notes, RAL nearest match, LRV, chroma, WCAG contrast data, and Colour Memory branding. Use this to create client deliverables, specification sheets, and print assets. TRUST BOUNDARY: every colour rendered in this PDF is verified server-side against the real archive by (name, hex, archive_source) before it is drawn -- any claim_strength, primary_source, colour_notes, colour_basis, or hex_confidence supplied in `entries`/`sections` is IGNORED and replaced with Colour Memory's own record for that colour; an entry that matches no real archive record refuses the whole request (PDF_ENTRY_NOT_VERIFIED) rather than being dropped or rendered with the caller's claim. Two supported entry sources: (1) the flat entries array from query_hex or palette_from_concept -- each item needs name, hex, archive_source (colour_notes/primary_source/zone may be supplied but are ignored/overwritten by the server-verified record); or (2) archive_report_brief's output -- pass report['presented_cards'] as entries, NOT report['colour_cards'] (the legacy field is kept only for backward compatibility and does not carry family-card presentation). presented_cards may mix three card shapes, all rendered as exactly one page each regardless of how many underlying records they represent: single_cultivar (a normal flat card), colour_family (card_type='colour_family', many near-identical records summarised as one card with member_count/supported_by/family_delta_e_max -- every member is verified individually, and representative_hex must be one of the verified members' own hexes), and conservative-mode hero cards (a single_cultivar card carrying family_grouping_suppressed=true and also_supported_by, representing a larger natural family that was folded into one promoted cultivar instead of shown as a group). delivery controls how the PDF is returned: 'url' (default) gives a signed, time-limited R2 download link; 'base64' returns the PDF bytes inline in the response for callers that need the file directly rather than a link. This tool requires a valid, authenticated API key EXCEPT when using `house_ref` alone (anonymous house_ref access is unchanged) -- `entries`, `sections`, and `project_id` all require a key; a keyless request to those returns 401. No extra credit is charged for the key check itself. Alternative input mode: pass `sections` instead of `entries` for a grouped, multi-section document (e.g. house_specify's rooms) instead of one page per flat colour card. Each section has `entries` (verified exactly like the flat-entries path above) and, optionally, `grouping_basis`/`hero_hex`. DO NOT send `title`, `subtitle`, `rationale`, or `application_notes` on a section -- these are requester free text, and this renderer cannot currently keep them cleanly separated from Colour Memory's own evidence, so any of them being present REFUSES THE WHOLE REQUEST with a 400 (REQUESTER_FREE_TEXT_NOT_ALLOWED) naming the offending field(s); a section with only `entries` still renders, with an auto-numbered heading. `presentation.template` picks the layout: 'sectioned_specification' (clean grid-per-section spec sheet) or 'colour_drenched_lookbook' (hero colour fills the page, swatches cover most of it, citations collected into a final appendix rather than shrunk onto every page). Third input mode: pass `house_ref` (NOT `house`) -- the reference string house_specify's own response returns -- for the flagship document-plan pipeline: a complete, editorial multi-archetype publication with a cover, a house_thesis argument page, a whole_house_progression chart, one room_hero + one implementation (practical specification) page per room, and a redesigned source_appendix, all sharing one design system. house_ref (or project_id, for an authenticated caller's own durable project) is the ONLY way to reach this pipeline: passing the house_specify response object itself as an inline `house` field is REFUSED outright (400, INLINE_HOUSE_NOT_ALLOWED) -- this PDF is Colour Memory-branded, and it can only render a house Colour Memory itself created and still holds, never one relayed back through the request body, even unmodified. Call house_specify first, then pass the house_ref it returns here. house_ref/project_id takes priority over `sections`/`entries` when supplied.

  Paramètres, retour & exemple (11)

  Paramètres

  • house · object · optionnel
    DO NOT USE. Inline house objects are REFUSED outright (400, INLINE_HOUSE_NOT_ALLOWED), even alongside a valid house_ref/project_id -- this PDF is Colour Memory-branded and can only render a house Colour Memory itself created and still holds, never one relayed back through the request body. Call house_specify, then pass the house_ref it returns in `house_ref` below instead.
  • query · string · optionnel
    Optional title for the palette e.g. Ottoman imperial luxury
  • source · string · optionnel
    Optional source label e.g. brand, conceptual
  • verify · boolean · optionnel
    Issue as a Verified by Colour Memory document (Colour Memory Pro).
  • entries · array · optionnel
    Array of colour cards. Either the flat entries array from query_hex/palette_concept, or report['presented_cards'] from archive_report_brief (single_cultivar, colour_family, and conservative-mode hero cards are all supported -- see tool description). Omit if using `sections` instead. EVIDENCE FIELDS ARE SERVER-VERIFIED: each entry's name+hex(+archive_source) must match a real archive record -- any claim_strength/primary_source/colour_notes/colour_basis/hex_confidence supplied here is ignored and replaced with Colour Memory's own record; a non-matching entry refuses the whole request. Requires a valid API key.
  • delivery · string · optionnel · url | base64
    'url' (default): signed, time-limited R2 download link. 'base64': PDF bytes returned inline as pdf_base64 for callers that need the file directly.
  • sections · array · optionnel
    Alternative to `entries` -- one entry per document section, e.g. house_specify's rooms. Each: {grouping_basis?, hero_hex?, entries: [...colour cards, server-verified exactly like the flat `entries` field above...]}. DO NOT include title/subtitle/rationale/application_notes -- this renderer cannot currently keep that requester free text cleanly separated from Colour Memory's own evidence, so any of them present REFUSES THE WHOLE REQUEST with 400 REQUESTER_FREE_TEXT_NOT_ALLOWED naming the field(s); a section with only `entries` still renders, with an auto-numbered heading. Requires a valid API key.
  • house_ref · string · optionnel
    THE way to render the flagship document-plan publication -- the house_ref string house_specify's own response returns (valid for 30 minutes after that call, or per project_persistence for a durable/temporary project). Renders the identical flagship document without resending the house object over the wire, and without it ever being treated as caller-supplied evidence. Anonymous house_ref access needs no API key, unchanged; do not send `house` alongside it.
  • project_id · string · optionnel
    Alternative to house_ref for an authenticated (keyed) caller's own durable project -- the project_id house_specify returned. Requires the same API key that created the project.
  • presentation · object · optionnel
    Used with `sections` or `house_ref`/`project_id`. {template: 'sectioned_specification'|'colour_drenched_lookbook' (sections only), page_size?: 'A4-portrait'|'A4-landscape'|'16:9', minimum_colour_coverage?: number (default 0.55 for lookbook), source_display?: 'inline'|'appendix', max_body_words_per_page?: integer, min_body_font_pt?: number (default 10.5), min_label_font_pt?: number (default 9, swatch colour-name labels), min_citation_font_pt?: number (default 7.5, appendix citations and page furniture)}. No rendered text falls below its category's floor -- names that don't fit are truncated with an ellipsis, never shrunk past the floor.
  • project_version · integer · optionnel
    Used with either house_ref or project_id -- render this specific immutable version instead of the project's current version. Omit to render the current version.

  Exemple d'appel

  {"name": "palette_pdf", "arguments": {"house": {}, "query": "texte", "source": "texte", "verify": true, "entries": [], "delivery": "url"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_specify≈ 322 tokens

  Generate a complete interior specification from 2-8 hex values. Returns surface assignments, 60-30-10 proportions, lighting behaviour, and archive colour names. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (3)

  Paramètres

  • style · string · optionnel
    e.g. 'heritage', 'contemporary', 'minimal'
  • colours · array · requis
    List of 2-8 hex values
  • room_type · string · optionnel
    e.g. 'living', 'bedroom', 'kitchen', 'study'

  Exemple d'appel

  {"name": "palette_specify", "arguments": {"colours": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_strict≈ 425 tokens

  Like palette_concept but with archive filtering and relevance controls. Use allowed_archives to restrict results to specific cultural traditions e.g. ['Japan'] for Japanese only. Use min_relevance to filter weak concept matches. Fixes cross-archive drift when cultural specificity matters. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (5)

  Paramètres

  • concept · string · requis
    Cultural concept e.g. Japanese wabi-sabi
  • n_colours · integer · optionnel
    Number of colours (default 5)
  • min_relevance · number · optionnel
    Minimum relevance score 0-1 (default 0.3)
  • allowed_archives · array · optionnel
    Archive names to restrict results e.g. ['Japan', 'China']
  • include_neutrals · boolean · optionnel
    Include neutral tones (default true)

  Exemple d'appel

  {"name": "palette_strict", "arguments": {"concept": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_swatch≈ 362 tokens

  Generate a clean, text-free PNG swatch image from hex colours. Returns a URL to the PNG. Use for Midjourney --sref style references or design mood boards. Supports photo-proportional weights from palette extraction, equal distribution, grid layout, a true smooth LCh-interpolated gradient (no hard colour edges, best for mood/atmosphere/colour-grade references rather than literal composition), and 13 fixed design ratios (6310, 7020, triptych, quad, filmstrip, etc.).

  Paramètres, retour & exemple (5)

  Paramètres

  • h · integer · optionnel
    Output height in pixels (default 630)
  • w · integer · optionnel
    Output width in pixels (default 1200)
  • hexes · string · requis
    Comma-separated hex values e.g. #d4a829,#1a5c6e,#0a0a0b
  • layout · string · optionnel
    photo | equal | grid | gradient | filmstrip | 6310 | 7020 | 5030 | 8010 | 5050 | 6040 | triptych | quad | 55-25-20 | quint | 70-10-20 | 40-30-20-10 | 33-33-24-10. gradient is a true smooth perceptual blend with no hard edges, unlike every other layout here.
  • weights · string · optionnel
    Comma-separated proportional weights from k-means extraction. Used only when layout=photo.

  Exemple d'appel

  {"name": "palette_swatch", "arguments": {"hexes": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_translate≈ 438 tokens

  Map any list of hex values into a target archive using CIEDE2000 nearest-neighbour matching. Each input hex is matched to the closest named colour in the chosen archive, with a delta-e relevance band (exact / close / approximate / loose) and full provenance. Use to translate a client's paint colours into Shakespeare language, map a brand palette into historical Japanese pigments, or find the nearest Oxfordshire equivalents to a French scheme. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (3)

  Paramètres

  • palette · array · requis
    List of hex values to translate e.g. ['#F5F0E8', '#8B6B3D']
  • max_delta_e · number · optionnel
    Max acceptable CIEDE2000 distance — above this is flagged out-of-threshold (default 40)
  • target_archive · string · requis
    Archive to translate into e.g. 'Shakespeare', 'Japan', 'Oxfordshire'

  Exemple d'appel

  {"name": "palette_translate", "arguments": {"palette": [], "target_archive": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• palette_verdict≈ 453 tokens

  Evaluate a palette of 2-8 hex values for a use case, market, and medium. Returns a verdict (strong / strong_with_adjustment / weak / avoid), a score 0-100, the role of each colour, the single biggest weakness, and a concrete suggestion for what to add to fix it. Each colour is matched to the nearest archive entry for cultural grounding. Examples: 'premium cushion collection UK ecommerce', 'hotel lobby interior', 'SaaS brand identity global digital'. The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (4)

  Paramètres

  • market · string · optionnel
    Optional: target market e.g. 'UK', 'Japan', 'global'
  • medium · string · optionnel
    Application medium e.g. 'interior', 'digital', 'fashion', 'print'
  • palette · array · requis
    List of 2-8 hex values e.g. ['#31559B', '#E8D898', '#4A2A50']
  • use_case · string · requis
    What the palette will be used for e.g. 'luxury cushion collection', 'brand identity'

  Exemple d'appel

  {"name": "palette_verdict", "arguments": {"palette": [], "use_case": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• project_delete≈ 195 tokens

  Soft-delete a durable house project you own. Idempotent -- deleting an already-deleted, unknown, or not-owned project_id returns the same successful-shaped response either way, and never discloses which case occurred. Version rows are never physically erased. Once deleted, a project can no longer be resolved by project_id or house_ref.

  Paramètres, retour & exemple (1)

  Paramètres

  • project_id · string · requis
    The project_id returned by house_specify for an authenticated (keyed) call.

  Exemple d'appel

  {"name": "project_delete", "arguments": {"project_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• project_export≈ 764 tokens

  Export the same house-flagship content palette_pdf renders as a genuinely editable Word document or Excel workbook -- for a client who needs to annotate the scheme, or a contractor building a materials/procurement schedule from it. Accepts exactly one of house_ref or project_id -- an inline house object is refused (400) (same resolution and ownership rules as palette_pdf: an authenticated project_id or house_ref requires its owner; an anonymous temporary house_ref works bearer-only). Never calls house_specify, never re-runs reasoning or re-matches archives -- it renders exactly what was already resolved and stored. DOCX mirrors the PDF flagship's structure (title page, house thesis, whole-house progression, one section per room, implementation details with the same historical/digital-estimate/commercial-candidate distinction, and a deduplicated source appendix) as real editable paragraphs and tables, never images. XLSX produces three sheets: Finishes Schedule (one row per room-surface-colour assignment), Evidence Register (one row per unique colour, the full citation/claim-strength/do_not_say trail), and Paint Procurement (one row per unique paint product, deduplicated for ordering). Every field left blank where the underlying stored data doesn't have it -- nothing is invented. delivery="url" (default) gives a signed R2 download link; delivery="base64" returns the file inline unless the encoded result is too large, in which case it fails closed with OUTPUT_TOO_LARGE_FOR_INLINE_DELIVERY and a repair instruction to use delivery="url" instead.

  Paramètres, retour & exemple (6)

  Paramètres

  • house · object · optionnel
    DO NOT USE -- an inline house object is refused (400 INLINE_HOUSE_NOT_ALLOWED). Pass house_ref (returned by house_specify) or project_id instead.
  • format · string · requis · docx | xlsx
    Which editable format to produce.
  • delivery · string · optionnel · url | base64
    'url' (default): signed, time-limited R2 download link. 'base64': file bytes returned inline as file_base64, unless too large -- see OUTPUT_TOO_LARGE_FOR_INLINE_DELIVERY.
  • house_ref · string · optionnel
    The house_ref string house_specify returns. For a durable (authenticated) project this also requires the same API key that created it.
  • project_id · string · optionnel
    The project_id returned by house_specify for an authenticated (keyed) call. Requires the same API key that created the project.
  • project_version · integer · optionnel
    Used with either house_ref or project_id -- export this specific immutable version instead of the project's current version. Omit to export the current version.

  Exemple d'appel

  {"name": "project_export", "arguments": {"format": "docx"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• project_get≈ 276 tokens

  Retrieve summary metadata for a durable house project you own -- title, project type, current version number, schema/archive revision, created/updated timestamps, and the content hash of the requested version. Requires an API key; the project must belong to the calling key. Does NOT return the full house specification (rooms, colours, sources) -- use house_ref with palette_pdf to render a document from a project, or project_versions to see its version history. An unknown, deleted, expired, or not-owned project_id all return the same generic not-found response, by design.

  Paramètres, retour & exemple (2)

  Paramètres

  • version · integer · optionnel
    Specific version number to describe. Omit for the project's current version.
  • project_id · string · requis
    The project_id returned by house_specify for an authenticated (keyed) call.

  Exemple d'appel

  {"name": "project_get", "arguments": {"project_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• project_list≈ 286 tokens

  List durable house projects owned by the calling API key, most recently updated first. Anonymous (keyless) calls always return an empty list -- temporary anonymous projects are never listable, only resolvable directly by their house_ref. Requires an API key.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · integer · optionnel
    Max projects to return, default 50, capped at 200.
  • cursor · string · optionnel
    Opaque pagination cursor -- pass the previous response's next_cursor to get the next page.
  • project_type · string · optionnel
    Filter by project type, e.g. 'house'. Omit for all types.
  • updated_since · string · optionnel
    ISO 8601 timestamp -- only return projects updated after this time.
  • include_deleted · boolean · optionnel
    Include soft-deleted projects (still owner-scoped). Default false.

  Exemple d'appel

  {"name": "project_list", "arguments": {"limit": 1, "cursor": "texte", "project_type": "texte", "updated_since": "texte", "include_deleted": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• project_versions≈ 190 tokens

  List every stored version of a durable house project you own, oldest first, with each version's content hash, build/schema/archive revision, and creation time. Version 1 is always immutable and always present. Earlier versions remain renderable via palette_pdf's project_version input even after a newer version exists. Requires an API key and ownership.

  Paramètres, retour & exemple (1)

  Paramètres

  • project_id · string · requis
    The project_id returned by house_specify for an authenticated (keyed) call.

  Exemple d'appel

  {"name": "project_versions", "arguments": {"project_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• query_conceptual≈ 356 tokens

  Ask a cultural, historical, or material colour question. Returns named archive colours with provenance and cultural context. Works for abstract queries like 'grief' (returns Ophelia Violet, Titan's Grief), 'toxic Victorian pigments' (returns Nightshade Poison Berry Purple, Victorian Arsenic Mirror Silver), or 'the sea at dusk' (returns Evening Sea, Thames Blue Dusk). Even a vague or personal-sounding query never comes back empty -- result_path in the response tells you honestly whether this was a 'direct' hit, a 'broadened' retry (relaxed match threshold), or a 'redirected' fallback (dropped an archive restriction or switched to full-corpus semantic search).

  Paramètres, retour & exemple (3)

  Paramètres

  • query · string · requis
    The colour concept or cultural question to search for
  • archive · string · optionnel
    Optional: restrict to a named archive e.g. 'Japan', 'Pigment', 'OttomanEmpire'
  • n_results · integer · optionnel
    Number of results (default 5)

  Exemple d'appel

  {"name": "query_conceptual", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• query_hex≈ 195 tokens

  Find the closest named archive colours to a hex value using CIEDE2000 perceptual distance.

  Paramètres, retour & exemple (3)

  Paramètres

  • hex · string · requis
    Hex value with or without # e.g. '#8B4513'
  • archive · string · optionnel
    Optional: restrict to a named archive
  • n_results · integer · optionnel
    Number of results (default 5)

  Exemple d'appel

  {"name": "query_hex", "arguments": {"hex": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• render_colour_result≈ 952 tokens

  Show a finished colour result to the customer AS COLOUR. Call this last, once the palette, house scheme, brand system or audit you are going to hand over has been decided -- it presents what you already have and chooses nothing. Do not call it for a single contrast figure, a colour history question with no palette, or tool guidance. Send the story with it: one sentence on what the scheme IS, the design decision you made, and the one rule worth remembering. The colours cannot carry those on their own.

  Paramètres, retour & exemple (14)

  Paramètres

  • kind · string · optionnel
    palette, house, brand or audit.
  • rooms · array · optionnel
    For a multi-room scheme: one short line per room, in your own words. What that room is doing with the palette.
  • title · string · optionnel
    What this result is, in the customer's terms.
  • bridge · object · optionnel
    Where the evidence started and where you took it. Include `colours` on a side ONLY if you have real colour values for it -- an invented source swatch beside a real archive one reads as evidence and is not.
  • checks · array · optionnel
  • colours · array · requis
    The colours you are handing over, in order.
  • verdict · string · optionnel
    One sentence, shown under the colour.
  • key_rule · string · optionnel
    The one rule worth remembering, short enough to repeat to a decorator. 'Boathouse Clay stays tiny. Never a wall.'
  • design_move · string · optionnel
    At most two sentences on the decision you made -- what the evidence offered and what you did with it. This is usually the most interesting thing in your answer and the part a list of colours cannot carry.
  • proportions · array · optionnel
    Only where a real share was decided. Every colour gets one and they total 100, or leave this out entirely -- a share nobody decided reads as a measurement nobody took.
  • story_thesis · string · optionnel
    ONE sentence: what this scheme IS. 'Danish coastal colour, domesticated for a summer house.' Shown above the palette, so it must earn its line.
  • evidence_thread · array · optionnel
    Three to five short sources or references that shaped this. Orientation, not a bibliography.
  • evidence_summary · string · optionnel
  • evidence_boundary · string · optionnel
    What is source-backed and what is your interpretation. Say it plainly: 'Designed contemporary interpretation, not a measured historical paint specification.'

  Exemple d'appel

  {"name": "render_colour_result", "arguments": {"colours": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• session_brief≈ 567 tokens

  Single-call forensic colour brief generator. Runs coverage gap analysis, pulls best archive colours, checks for anachronisms, scores claim roles (anchor/support/analogue/provocation/reject), auto-rejects stubs, generates editorial argument, act structure, pull quote, closing line, and image prompt via Claude. This replaces chaining coverage_gap + archive_report_brief + anachronism_guard + resonance_index + evidence_gap separately. Input: title, audience, themes, archives, period, tone. Output: complete deliverable package ready for PDF or editorial use. Tone options: forensic (default), editorial, clinical, narrative.

  Paramètres, retour & exemple (13)

  Paramètres

  • tone · string · optionnel
    forensic | editorial | clinical | narrative
  • avoid · array · optionnel
    Themes to suppress
  • title · string · optionnel
    Brief title e.g. 'The Colours of Pleasure'
  • themes · array · requis
    Research themes
  • archives · array · optionnel
    Archives to draw from
  • audience · string · optionnel
    Target audience e.g. 'serious collector'
  • n_colours · integer · optionnel
    Number of colour cards (default 8)
  • period_end · integer · optionnel
    End year e.g. 1830
  • period_start · integer · optionnel
    Start year e.g. 1714
  • target_period · string · optionnel
    Historical period e.g. 'Georgian England 1714-1830'
  • strict_sources · boolean · optionnel
    Only include entries with named primary sources
  • confidence_threshold · number · optionnel
    Min confidence 0-1 (default 0.6)
  • minimum_claim_strength · string · optionnel
    Hard evidence-grade floor: A, B, C, D, or E. Never silently relaxed.

  Exemple d'appel

  {"name": "session_brief", "arguments": {"themes": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• style_match≈ 564 tokens

  The colour question every stylist gets asked: does this bag go with this outfit? Submit your outfit items as hex values with labels (dress, bag, shoes, coat, belt, scarf, etc.) and receive a verdict on what works, what clashes, what is missing, and what to add. Pairs are judged on hue relationship and lightness contrast; each item is named from its nearest archive record, with that record's evidence grade and source. The archive documents single colours, not outfits, so it makes no claim that a combination has historical precedent. Also suggests one missing archive colour that would complete the look. Examples: 'I have a navy dress (#1C3A6E) and a tan bag (#C8A87A) — what shoes?' or 'Does this burgundy coat work with olive trousers?' The result already carries the rendered palette and its PNG, PDF, ASE, JSON and CSS downloads -- show them to the customer. Never present the archive anchors a colour was derived from as the colours you are recommending. If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours so the customer can see and download what you actually recommended.

  Paramètres, retour & exemple (3)

  Paramètres

  • ask · string · optionnel
    Optional: specific question e.g. 'what bag colour works?' or 'do the shoes work?'
  • items · array · requis
    List of outfit items with label and hex colour
  • occasion · string · optionnel
    Optional: occasion context e.g. 'daytime', 'evening', 'office', 'casual', 'wedding guest'

  Exemple d'appel

  {"name": "style_match", "arguments": {"items": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• system_status≈ 238 tokens

  Zero-argument diagnostic call: returns exactly what build is live right now (build_sha, schema_version, schema_hash, archive_revision, tool_count, generated_at, server_environment). Use this to confirm you're seeing the current deployed schema -- e.g. if a tool you expect (like house_specify) seems to be missing, call this first and compare schema_hash against another connection before assuming the server is wrong; a mismatch usually means one connection is holding a stale cached manifest, not a real deployment gap.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "system_status", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• tool_guide≈ 282 tokens

  Deterministic tool-routing lookup -- not an LLM call, always instant, never consumes archive or LLM credit. Give it a goal in plain words (e.g. 'I have a brand colour and want to check it against competitors', 'I want to paint a whole house', 'I have a photo and want the colours from it') and it returns exactly which tool to call first, what to call next, and which superficially-similar tools NOT to start with and why. Use this before guessing between similarly-named tools (e.g. palette_specify vs interior_specify vs house_specify, or colour_passport vs colour_dna).

  Paramètres, retour & exemple (1)

  Paramètres

  • goal · string · requis
    Plain-English description of what you're trying to do.

  Exemple d'appel

  {"name": "tool_guide", "arguments": {"goal": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"then": [], "reason": "texte", "start_with": "texte", "do_not_start_with": []}}

• ui_states≈ 285 tokens

  Generate a complete WCAG-compliant UI state palette from a brand hex. Returns colours for: brand, hover, active, disabled, focus ring, success, warning, error, info, surface subtle, surface strong. All states computed for contrast against your background colour. Returns hex, contrast ratio, WCAG grade, and usage note for each state. Includes CSS custom properties ready to paste. Supports light and dark mode. Use before building any UI component system.

  Paramètres, retour & exemple (3)

  Paramètres

  • brand_hex · string · requis
    Brand colour hex e.g. '#D4A829'
  • dark_mode · boolean · optionnel
    Generate for dark mode (default false)
  • background_hex · string · optionnel
    Background hex (default #FFFFFF)

  Exemple d'appel

  {"name": "ui_states", "arguments": {"brand_hex": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• vanderpoel_pairing≈ 725 tokens

  Emily Noyes Vanderpoel's documented 'good' dyad/triad hue groupings (Color Problems, 1902, Plate XXXVI 'Good Dyads or Pairs' and Plate XXXVII 'Good Triads'), served from the build artefacts vanderpoel_dyads.json and vanderpoel_triads.json. Snaps an input hex to the nearest of Vanderpoel's eleven real hue-family labels, resolves that hex against the archive, and returns every documented dyad or triad the label belongs to -- each OTHER member carrying its own nearest real archive match (CIEDE2000), with hex_collision disclosed when the match is tied. Unlike hay_contrast, this carries NO proportional ratio -- only Vanderpoel's own categorical 'good' editorial judgement, printed verbatim on the plates. Returns groupings: null for a near-neutral input, where hue is not meaningfully defined, or when the nearest hue-family label is a member of no dyad or triad -- silence is the honest answer, not a forced match. Member names come from a transcriber's digitisation_alt_text (an accessibility description of the plate image), not verified printed captions; every response states this caveat explicitly (member_source_caveat), not just a code comment. The hue positions used to snap an input to a label are a modern matching convention, not a number Vanderpoel printed -- disclosed per response as label_placement_basis.

  Paramètres, retour & exemple (2)

  Paramètres

  • hex · string · requis
    Hex colour, e.g. '#CC1A14'.
  • n_per_member · integer · optionnel
    Archive candidates per partner member (1-5). Default 1, which returns a single archive_match object rather than a list.

  Exemple d'appel

  {"name": "vanderpoel_pairing", "arguments": {"hex": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"reason": "texte", "covered": true, "groupings": [], "input_hex": "texte", "input_snapped_to": "texte", "input_archive_match": {}, "member_source_caveat": "texte", "label_placement_basis": "texte", "degrees_from_nearest_named_hue": 1}}

• why_connected≈ 302 tokens

  Are these two specific archive records connected -- and if so, exactly why? Traces the real path between them through Colour Memory's stored relationship graph (e.g. two Wada colours that share membership in the same published combination) and returns the actual path, not just a yes/no. States plainly when two records are NOT connected, and always states what a shared connection does not prove -- e.g. that two colours sharing a Wada combination were independently asserted as a pair, not just co-published in the same numbered plate. Get record_id values from archive_search or colour_card.

  Paramètres, retour & exemple (2)

  Paramètres

  • a · string · requis
    First record id.
  • b · string · requis
    Second record id.

  Exemple d'appel

  {"name": "why_connected", "arguments": {"a": "texte", "b": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"hops": 1, "path": [], "connected": true, "explanation": "texte", "does_not_mean": []}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://api.colourmemory.com/mcp