ai.ravenmcp/raven-mcp

Est-ce que ai.ravenmcp/raven-mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.ravenmcp/raven-mcp » 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 45 outils

• audit_consistency≈ 494 tokens

  Audit multiple pages for cross-page consistency of content-container width and hero heading tier. Pass ≥2 pages ({name, html}) collected from different routes on the same site. Infers the canonical (modal) value from the corpus when no token is supplied, so you need not know the project's design token in advance. Flags the issue #9 single-blob blind spot: pages that each pass audit_page but silently disagree with each other on container width or hero size class. Returns per-page extraction (container_px, container_classes, hero_classes, signatures), consistency dimensions with reference values, outlier page names, issues[], score (100/50/0 → A/C/D), and a plain-text summary. Pure offline — no browser, no network.

  Paramètres, retour & exemple (3)

  Paramètres

  • pages · array · requis
    At least 2 pages to compare. Each entry is {name, html}.
  • hero_token · string · optionnel
    Canonical hero heading class signature (e.g. "text-display-xl" or "64"). When supplied, hero divergence is measured against this token rather than the corpus modal.
  • container_token · number · optionnel
    Project's canonical container width in px (e.g. 1152). When supplied, container divergence is measured against this token rather than the corpus modal.

  Exemple d'appel

  {"name": "audit_consistency", "arguments": {"pages": []}}

  Exemple de retour

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

• audit_content≈ 471 tokens

  Evaluate an array of content items (headings, prose, CTAs, labels, captions, metrics, outcomes) against UX-writing principles and deterministic heuristics. Returns a per-item verdict (pass/warn/fail) with matched principle ids, concrete issues grounded in principle text, a before→after rewrite suggestion, and an aggregate summary. Heuristics: metric items must carry a number+unit; cta/label must be action-led and ≤4 words; prose flags passive voice, jargon, and hedging; headings flag filler openers and buzzwords; captions flag duplication of any heading in the batch. Pure offline — no network or browser. Use this instead of evaluate_design when you need per-item content verdicts rather than the principle library.

  Paramètres, retour & exemple (3)

  Paramètres

  • goals · array · optionnel
    Optional content goals (e.g. ['clarity','conversion']); recorded for traceability.
  • items · array · requis
    Array of content items to audit.
  • system · string · optionnel
    Optional content-system id (e.g. 'ux-writing'); recorded for traceability.

  Exemple d'appel

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

  Exemple de retour

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

• audit_contrast≈ 380 tokens

  Compute WCAG contrast ratios for every text element on a rendered page (pass url) or from a supplied dom_snapshot. Reports AA (4.5:1 normal, 3:1 large) and AAA pass/fail and surfaces failing pairs with selector, ratio, and delta-to-pass — replacing manual eyedropper + ratio math. dom_snapshot mode returns a row per supplied element; url mode returns counts plus every row that needs action (aa_failures, indeterminate_bg_rows) and OMITS the per-element rows for passing elements, because a real page produces hundreds of thousands of characters of them.

  Paramètres, retour & exemple (3)

  Paramètres

  • url · string · optionnel
    URL to render and measure (http/https or file://)
  • screenshot · string · optionnel
    Optional base64 PNG for caller reference; ratios are computed from the DOM, not pixels
  • dom_snapshot · array · optionnel
    Pre-collected text elements to score without rendering

  Exemple d'appel

  {"name": "audit_contrast", "arguments": {"url": "texte", "screenshot": "texte", "dom_snapshot": []}}

  Exemple de retour

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

• audit_ios_a11y≈ 412 tokens

  Score an accessibility-enriched iOS element snapshot — missing accessibilityLabel/value/traits, sub-44pt tap targets, per-text WCAG contrast, Dynamic Type clipping, and VoiceOver reading order. Provide {elements:[{label,value,hint,traits,role,rect,fontPt,fgColor,bgColor,dynamicTypeClipped}],viewport}. Capture via the AccessibilitySnapshot XCUITest / ios-capture harness.

  Paramètres, retour & exemple (3)

  Paramètres

  • options · object · optionnel
  • elements · array · requis
  • viewport · object · requis

  Exemple d'appel

  {"name": "audit_ios_a11y", "arguments": {"elements": [], "viewport": {}}}

  Exemple de retour

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

• audit_ios_privacy≈ 441 tokens

  Audit an iOS or React Native/Expo app's privacy posture for App Review and user trust. Reads a native Info.plist XML OR an Expo app.json (managed Expo apps have no Info.plist) — plus optional PRIVACY.md, entitlements, and source. Flags: NS*UsageDescription strings that are vague/missing or contradict the code (e.g. a HealthKit write claim the code never fulfills), entitlements/permissions and Android permissions the app doesn't use, ATS cleartext exceptions and non-HTTPS endpoints, secrets/keys shipped in the bundle or app.json, and default data-egress paths not disclosed at the point of choice (a pre-selected 'Recommended' option that silently sends personal data to a server). Same return shape as audit_page.

  Paramètres, retour & exemple (5)

  Paramètres

  • source · string · optionnel
    Optional concatenated source (Swift or JS/TS) — enables code-vs-declaration contradiction checks and default-egress detection
  • app_json · string · optionnel
    Expo app.json / app.config JSON (managed RN). Its expo.ios.infoPlist, expo.android.permissions, plugins, and extra are audited.
  • info_plist · string · optionnel
    Raw Info.plist XML (native iOS / bare RN). Provide this OR app_json.
  • privacy_md · string · optionnel
    Optional PRIVACY.md / privacy policy text to cross-reference against declared permissions and default behavior
  • entitlements · string · optionnel
    Optional .entitlements XML

  Exemple d'appel

  {"name": "audit_ios_privacy", "arguments": {"source": "texte", "app_json": "texte", "info_plist": "texte", "privacy_md": "texte", "entitlements": "texte"}}

  Exemple de retour

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

• audit_ios_screen≈ 721 tokens

  Audit a rendered iOS screen from a view-hierarchy/accessibility snapshot (and optional screenshot). Alias of audit_screen with platform:"ios". Call with no arguments for the expected snapshot shape. Call with {elements:[{label,rect:{x,y,w,h},role,fontPt,fgColor,bgColor}],viewport:{w,h}} to score 44×44pt touch targets, contrast (with iOS secondaryLabel/tertiaryLabel treated as platform-standard — warn not fail), and visual rhythm (alignment, gap consistency, optical balance) in points. Same return shape as audit_page. Taste-profile bindings are not available on the hosted (remote) endpoint (per-user state is a later phase). Omit 'project'/'profile' to run the stateless iOS screen audit.

  Paramètres, retour & exemple (5)

  Paramètres

  • profile · string · optionnel
    Taste profile owning the binding. Omit to search all stored profiles for one bound to the project.
  • project · string · optionnel
    Project identifier — resolves a saved taste surface binding (see bind_taste_surface). When the binding carries design_notes and a screenshot is passed, the screenshot's pixels verify the color-scheme notes; results gain note_assessments.
  • elements · array · optionnel
    Elements captured from the rendered screen via an accessibility/view-hierarchy snapshot
  • viewport · object · optionnel
    Screen size in pt (iOS) or dp (Android) at capture time, e.g. {w:393,h:852} iPhone 15, {w:412,h:915} Pixel
  • screenshot · string · optionnel
    Optional base64 PNG of the screen, for the caller's reference. Geometry is scored from the snapshot, not decoded pixels.

  Exemple d'appel

  {"name": "audit_ios_screen", "arguments": {"profile": "texte", "project": "texte", "elements": [], "viewport": {}, "screenshot": "texte"}}

  Exemple de retour

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

• audit_layout≈ 400 tokens

  Evaluate visual rhythm from a rendered page's geometry. Call with no arguments to get a DevTools snippet to paste into your page — it prints {elements, viewport} JSON. Call again with that JSON to get alignment, gap-rhythm, and optical-balance scores. This is the complement to audit_page for things only visible once rendered.

  Paramètres, retour & exemple (2)

  Paramètres

  • elements · array · optionnel
    Array of element rects captured from the rendered page via the DevTools snippet
  • viewport · object · optionnel
    Viewport dimensions {w,h} at capture time

  Exemple d'appel

  {"name": "audit_layout", "arguments": {"elements": [], "viewport": {}}}

  Exemple de retour

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

• audit_page≈ 845 tokens

  Audit HTML/CSS against Raven's design quality standards. Checks typography (min 13px, weight 400+, modular-scale heading ratios, line-height consistency), accessibility (WCAG touch targets, alt text, contrast), responsive patterns (flexbox over grid, clamp sizing, max-width containers), style guide compliance (CSS custom properties, no bare hex), and visual rhythm (4/8px spacing grid, tight spacing scale, palette size). Pass containerMaxWidth (your design system's canonical container token, in px) to make the max-width check token-aware — it then flags containers that diverge from your system (too narrow OR too wide) instead of a generic 1200px heuristic. Returns pass/fail per check with specific fix instructions. NOTE: the url argument is REJECTED on this hosted (remote) endpoint - pass html instead. audit_page url-capture is disabled on the hosted (remote) endpoint. Pass the page HTML via the 'html' argument instead.

  Paramètres, retour & exemple (9)

  Paramètres

  • url · string · optionnel
    REJECTED on this hosted (remote) endpoint; pass html instead. (Local/stdio: Raven launches headless chromium, renders the page, and audits the RENDERED DOM.)
  • html · string · optionnel
    The full HTML content of the page to audit
  • strict · boolean · optionnel
    Strict mode — also flags warnings as failures. Default: false
  • compact · boolean · optionnel
    Return only the decision-grade signal — score, grade, summary, errors, warnings, fix_priority — and drop the embedded base64 screenshot and the passes list (replaced by passes_count). Default false. Use when the full payload would blow the tool-result budget.
  • viewport · object · optionnel
  • interactions · array · optionnel
    Before capturing, fire each interaction in order (hover/click/focus the selector, then wait delay_ms). Captures the resulting dynamic state — e.g. an on-hover theme-toggle wash invisible to a static screenshot.
  • scroll_settle · boolean · optionnel
    Before capturing, step through the page with short pauses so IntersectionObserver/whileInView reveals fire, then return to the top and settle. Also plays preload=none videos. Prevents blank-section false positives.
  • containerMaxWidth · number · optionnel
    Your design system's canonical content-container width in px (e.g. 1152). When set, the responsive/max-width check flags divergence from this token instead of using the generic 1200px heuristic.
  • adversarial_verify · boolean · optionnel
    After generating findings, independently re-check each against the live DOM/network and tag it confirmed / likely-artifact / inconclusive. Surfaces a debunked_count.

  Exemple d'appel

  {"name": "audit_page", "arguments": {"url": "texte", "html": "texte", "strict": true, "compact": true, "viewport": {}, "interactions": []}}

  Exemple de retour

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

• audit_parity≈ 639 tokens

  Compare iOS vs Android element snapshots against a checklist of named spatial relationships (vertical centering, baseline/left alignment, equal gap/size, presence, truncation) and flag per-relation match/mismatch/uncertain — catches cross-platform layout drift like status text centered on one platform but top-aligned on the other. Provide ios+android {elements,viewport} snapshots and a checklist[].

  Paramètres, retour & exemple (3)

  Paramètres

  • ios · object · requis
  • android · object · requis
  • checklist · array · requis

  Exemple d'appel

  {"name": "audit_parity", "arguments": {"ios": {}, "android": {}, "checklist": []}}

  Exemple de retour

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

• audit_responsive_visibility≈ 277 tokens

  Render a URL at multiple breakpoints and flag content elements that are visible on desktop but hidden on mobile (display:none / opacity:0 / visibility:hidden / zero-size). Categorises each flag as 'likely-oversight' (content that vanishes on mobile — the hidden-on-mobile content bug) vs 'intentional' (decorative). Returns a table of selector / hiding-class / mobile-visible / desktop-visible / category. Requires headless chromium.

  Paramètres, retour & exemple (3)

  Paramètres

  • url · string · requis
    URL to render (http/https or file://)
  • breakpoints · array · optionnel
    Viewport widths in px. Default [390, 768, 1440, 2160]
  • viewportHeight · number · optionnel
    Render height in px. Default 900

  Exemple d'appel

  {"name": "audit_responsive_visibility", "arguments": {"url": "texte"}}

  Exemple de retour

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

• audit_rn≈ 565 tokens

  Audit React Native / Expo source (JSX/TSX + StyleSheet) against the iOS HIG + Android Material conventions RN must satisfy. Flags touchables missing accessibilityLabel/accessibilityRole, touchables below 44pt without hitSlop, allowFontScaling={false}, fontSize below ~13, screens without SafeAreaView, and (for multi-mode apps) hardcoded colors with no useColorScheme/Appearance dark-mode handling. Rewards SafeAreaView, hitSlop, Platform-aware code, and a theme. RN-native checks only — no web/CSS or SwiftUI rules. Same return shape as audit_page. (RN renders to native widgets, so audit_ios_screen scores the rendered screen.) Taste-profile bindings are not available on the hosted (remote) endpoint (per-user state is a later phase). Omit 'project'/'profile' to run the stateless React Native audit.

  Paramètres, retour & exemple (5)

  Paramètres

  • source · ? · requis
    React Native source — a single screen/component as a string, or an array of file contents. Concatenated before analysis.
  • strict · boolean · optionnel
    Strict mode — also count warnings as failures for grading. Default: false
  • profile · string · optionnel
    Taste profile owning the binding. Omit to search all stored profiles for one bound to the project.
  • project · string · optionnel
    Project identifier — resolves a saved taste surface binding (see bind_taste_surface). When the binding carries design_notes, each note is verified against the source (Animated/Reanimated, BlurView, haptics, fonts) and returned in note_assessments; missing notes count toward the grade.
  • color_scheme · string · optionnel · light | dark | automatic
    The app's declared appearance (Expo app.json userInterfaceStyle). 'light' or 'dark' means single-mode by design — the dark-mode adaptation check is then suppressed. Default: automatic.

  Exemple d'appel

  {"name": "audit_rn", "arguments": {"source": "texte"}}

  Exemple de retour

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

• audit_screen≈ 784 tokens

  Audit a rendered mobile screen (iOS or Android) from a view-hierarchy/accessibility snapshot. Call with no arguments for the expected snapshot shape and how to capture it. Pass platform:"android" to score against the 48dp Material touch minimum and Material muted roles (onSurfaceVariant/outline = warn not fail); default platform:"ios" scores 44pt and treats secondaryLabel/tertiaryLabel as platform-standard. Both score touch targets, contrast, and visual rhythm (alignment, gap consistency, optical balance). Same return shape as audit_page. Taste-profile bindings are not available on the hosted (remote) endpoint (per-user state is a later phase). Omit 'project'/'profile' to run the stateless screen audit.

  Paramètres, retour & exemple (7)

  Paramètres

  • profile · string · optionnel
    Taste profile owning the binding. Omit to search all stored profiles for one bound to the project.
  • project · string · optionnel
    Project identifier — resolves a saved taste surface binding (see bind_taste_surface). When the binding carries design_notes and a screenshot is passed, the screenshot's pixels verify the color-scheme notes; results gain note_assessments.
  • elements · array · optionnel
    Elements captured from the rendered screen via an accessibility/view-hierarchy snapshot
  • platform · string · optionnel · ios | android
    Target platform — 'ios' (default, 44pt minimum, iOS semantic colors) or 'android' (48dp minimum, Material semantic roles)
  • viewport · object · optionnel
    Screen size in pt (iOS) or dp (Android) at capture time, e.g. {w:393,h:852} iPhone 15, {w:412,h:915} Pixel
  • screenshot · string · optionnel
    Optional base64 PNG of the screen, for the caller's reference. Geometry is scored from the snapshot, not decoded pixels.
  • scroll_settle · boolean · optionnel

  Exemple d'appel

  {"name": "audit_screen", "arguments": {"profile": "texte", "project": "texte", "elements": [], "platform": "ios", "viewport": {}, "screenshot": "texte"}}

  Exemple de retour

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

• audit_swiftui≈ 529 tokens

  Audit SwiftUI source against Apple's Human Interface Guidelines. Flags hardcoded .font(.system(size:)) below ~13pt and tiny semantic fonts (.caption/.caption2), hardcoded Color(red:green:blue:)/hex instead of asset-catalog or semantic system colors, an empty/undefined AccentColor, interactive frames below 44×44pt, and ad-hoc spacing off the 4/8-pt grid. Rewards semantic Dynamic Type fonts, semantic system colors, SF Symbols, and flexible frames. iOS-native checks only — no web/CSS rules. Returns pass/fail per check with fix instructions. Taste-profile bindings are not available on the hosted (remote) endpoint (per-user state is a later phase). Omit 'project'/'profile' to run the stateless SwiftUI audit.

  Paramètres, retour & exemple (5)

  Paramètres

  • source · ? · requis
    SwiftUI source — a single file/view as a string, or an array of file contents. Concatenated before analysis.
  • strict · boolean · optionnel
    Strict mode — also count warnings as failures for grading. Default: false
  • profile · string · optionnel
    Taste profile owning the binding. Omit to search all stored profiles for one bound to the project.
  • project · string · optionnel
    Project identifier — resolves a saved taste surface binding (see bind_taste_surface). When the binding carries design_notes, each note is verified against the source (animation/material/haptic/font APIs) and returned in note_assessments; missing notes count toward the grade.
  • accent_color_contents · string · optionnel
    Optional raw Contents.json of AccentColor.colorset. When provided, the tool verifies AccentColor actually defines color components (flags an empty/undefined accent color as an error).

  Exemple d'appel

  {"name": "audit_swiftui", "arguments": {"source": "texte"}}

  Exemple de retour

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

• audit_tap_targets≈ 378 tokens

  WCAG 2.5.5 / Apple 44pt tap-target audit for the web. Collects every interactive element (a, button, [role=button], input[type=submit/button/checkbox/radio], select, summary, label[for], [onclick], [tabindex>=0]) and emits a PER-ELEMENT fix table for any whose rendered width or height is below the minimum (default 44px): selector, role, visible text, measured w/h, pixel deficit per axis, and a concrete CSS fix. Sorted worst-first. Two modes: pass url (renders in headless chromium, measures real getBoundingClientRect) or pass elements[] snapshot (pure, no browser).

  Paramètres, retour & exemple (3)

  Paramètres

  • url · string · optionnel
    URL to render and measure. Requires headless chromium.
  • minSize · number · optionnel
    Minimum tap-target size in px on each axis. Default 44.
  • elements · array · optionnel
    Pre-collected interactive elements to score without rendering.

  Exemple d'appel

  {"name": "audit_tap_targets", "arguments": {"url": "texte", "minSize": 1, "elements": []}}

  Exemple de retour

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

• audit_typography≈ 441 tokens

  Audit the typographic SCALE of a rendered page (pass url) or a pre-collected snapshot of text nodes. Emits a focused report: (a) MODULAR SCALE — detects the dominant ratio (~1.2/1.25/1.333/1.5) across distinct font sizes and flags off-scale outliers; (b) LINE-HEIGHT CONSISTENCY — unitless lh/fs ratio per node, identifies the body rhythm and flags outliers; (c) WEIGHT LADDER — distinct weights, flags >4 weights or non-standard CSS values. Returns scale, line_height, weight_ladder, nodes_analyzed, and findings[{rule,severity,selector,message,fix}]. Goes beyond audit_page's pass/fail typography checks. NOTE: despite the mention of url above, url mode is DISABLED on this hosted (remote) endpoint - pass nodes instead. audit_typography url-capture is disabled on the hosted (remote) endpoint. Pass a 'nodes' snapshot instead of 'url'.

  Paramètres, retour & exemple (2)

  Paramètres

  • url · string · optionnel
    REJECTED on this hosted (remote) endpoint; pass nodes instead. (Local/stdio: URL to render and measure, http/https or file://; requires headless chromium.)
  • nodes · array · optionnel
    Pre-collected text nodes to analyze without rendering.

  Exemple d'appel

  {"name": "audit_typography", "arguments": {"url": "texte", "nodes": []}}

  Exemple de retour

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

• audit_url≈ 868 tokens

  Layer 0 render-and-capture audit: renders a LIVE URL at each viewport×theme, scroll-settles (fires whileInView/IntersectionObserver reveals; plays preload=none videos), optionally fires caller-supplied hover/focus/click interactions, and captures real pixels + the rendered DOM. Then runs the existing audit_page rule engine, per-element WCAG contrast, responsive-visibility (desktop-shown/mobile-hidden), blank-media detection, sliced-image edge symmetry, and hover-state white-wash detection over the captures. Every finding is tagged confirmed | likely-artifact | inconclusive with its evidence, ranked by severity. This is the tool that catches real-world visual nits invisible to HTML-string/geometry audits: cropped images, blank videos, hover white-wash, sliced exports, and hidden-on-mobile content. Requires headless chromium. audit_url is disabled on the hosted (remote) endpoint: one run drives a real browser through every requested viewport and theme, and was MEASURED at 95s in its cheapest single-viewport single-theme configuration and past 120s with defaults, which exceeds the per-call budget of the hosted clients that call it. Run it locally instead (npx raven-mcp) where there is no request deadline, or pass the page HTML to audit_page here for a static grade.

  Paramètres, retour & exemple (9)

  Paramètres

  • url · string · requis
    URL to render and audit (http/https or file://)
  • themes · array · optionnel
    Themes to toggle (prefers-color-scheme + data-theme/class). Default: ['light','dark']
  • compact · boolean · optionnel
    Drop per-capture base64 screenshots; keep findings, counts, and summary. Default false. Use when screenshots would blow the tool-result budget.
  • timeoutMs · number · optionnel
    Per-navigation timeout in ms. Default: 30000
  • viewports · array · optionnel
    Viewports to render. Default: iphone 393×852, desktop 1440×900, wide 2160×1200
  • interactions · array · optionnel
    Fire each interaction before capture; the resulting state is diffed against baseline to catch hover/click white-wash and obscured content.
  • scroll_settle · boolean · optionnel
    Step through the page with short pauses to fire reveal-on-scroll/IntersectionObserver content, play videos, then return to the top before capture. Default: true
  • containerMaxWidth · number · optionnel
    Your design system's canonical container width in px — makes the max-width check token-aware.
  • includeScreenshots · boolean · optionnel
    Include the base64 full-page PNG per capture in the result. Default: false (screenshots are large).

  Exemple d'appel

  {"name": "audit_url", "arguments": {"url": "texte"}}

  Exemple de retour

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

• audit_video_playback≈ 589 tokens

  Render a page in headless Chromium and observe whether each <video> actually advances (samples currentTime before/after a play attempt), classifying every clip into playing|paused|stalled|empty|error with a reason. Catches black/non-playing videos that static audits miss — the most common real-world defect on marketing sites with video backgrounds. Pass url to render + observe, or dom_snapshot to classify pre-collected observations without a browser.

  Paramètres, retour & exemple (3)

  Paramètres

  • url · string · optionnel
    URL to render and observe (http/https or file://). Requires headless chromium.
  • observeMs · number · optionnel
    Milliseconds to wait between currentTime samples after play() attempt. Default: 1000
  • dom_snapshot · array · optionnel
    Pre-collected video observations to classify without rendering (deterministic path)

  Exemple d'appel

  {"name": "audit_video_playback", "arguments": {"url": "texte", "observeMs": 1, "dom_snapshot": []}}

  Exemple de retour

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

• compose_system≈ 242 tokens

  Mix tokens from different design systems to create a custom composite. Example: Linear's colors + Stripe's typography.

  Paramètres, retour & exemple (2)

  Paramètres

  • format · string · optionnel · dtcg | css
    Output format. Default: dtcg
  • compositions · array · requis
    Array of system-group pairs to compose

  Exemple d'appel

  {"name": "compose_system", "arguments": {"compositions": []}}

  Exemple de retour

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

• evaluate_design≈ 389 tokens

  Evaluate a design description against UX principles. Returns relevant principles, potential violations, and improvement suggestions. Screenshot pixel-diff is disabled on the hosted (remote) endpoint (unbounded image decode). Omit 'before_screenshot'/'after_screenshot' and pass a 'description' to evaluate the design against UX principles statelessly.

  Paramètres, retour & exemple (6)

  Paramètres

  • goals · array · optionnel
    What to evaluate for (e.g. ['conversion', 'accessibility', 'mobile-usability'])
  • compact · boolean · optionnel
    Return only ids+names for matched principles/patterns (drop their full bodies) plus counts and any before/after diff. Default false. Use when the full principle library payload would blow the tool-result budget.
  • context · string · optionnel
    What the design is (e.g. 'pricing page for SaaS product')
  • description · string · optionnel
    Description of the design to evaluate
  • after_screenshot · string · optionnel
    Base64 PNG of the AFTER state. When both before+after are provided, returns a structured pixel diff with fix_confirmed.
  • before_screenshot · string · optionnel
    Base64 PNG of the BEFORE state

  Exemple d'appel

  {"name": "evaluate_design", "arguments": {"goals": [], "compact": true, "context": "texte", "description": "texte", "after_screenshot": "texte", "before_screenshot": "texte"}}

  Exemple de retour

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

• generate_design_system≈ 431 tokens

  Generate a complete, custom design system with full token set. Provide a brand color to auto-generate a harmonious palette, pick a style preset, and export as visual HTML documentation, CSS variables, W3C DTCG JSON, Figma Variables, or SVG palette card. The HTML export is a beautiful, self-contained page suitable for sharing with stakeholders.

  Paramètres, retour & exemple (6)

  Paramètres

  • name · string · requis
    Name for the design system (e.g. 'Acme Corp', 'NightOwl')
  • style · string · optionnel · minimal | bold | warm | corporate | playful | dark
    Aesthetic direction — influences spacing, radii, shadows, motion, and typography. Default: minimal
  • format · string · optionnel · html | css | dtcg | figma | svg | all
    Export format: html (visual doc page), css (custom properties), dtcg (W3C JSON), figma (Figma Variables JSON), svg (color palette card), all. Default: html
  • dark_mode · boolean · optionnel
    Generate dark mode tokens alongside light. Default: true
  • base_system · string · optionnel
    Start from an existing system as foundation (e.g. 'stripe', 'linear'). Colors will be replaced by brand_color if provided.
  • brand_color · string · optionnel
    Primary brand hex color (e.g. '#FF6B35'). Auto-generates a full harmonious palette using color theory.

  Exemple d'appel

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

  Exemple de retour

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

• generate_service_blueprint≈ 1049 tokens

  Render a service blueprint as a self-contained HTML page. Supports two modes: (1) classic Shostack single-actor blueprint — user action, frontstage, backstage, support, evidence, pain/delight; (2) two-actor HI-loop blueprint — when `actors` is supplied, renders two swim lanes with a line of interaction between them (e.g. customer ↔ lawyer, patient ↔ doctor, buyer ↔ agent). Each actor gets their own actions, frontstage (what they see), and evidence. Optionally accepts an ideal-state to render side-by-side with the current state.

  Paramètres, retour & exemple (5)

  Paramètres

  • ideal · array · optionnel
    Optional ideal-state blueprint — if provided, output shows current AND ideal side-by-side
  • actors · object · optionnel
    Omit for classic single-actor Shostack blueprint. Provide to render a two-swim-lane HI-loop blueprint with a line of interaction between the two sides.
  • current · array · requis
    The current-state blueprint as an array of steps
  • subtitle · string · optionnel
    Short description or context line under the title
  • service_name · string · requis
    Name of the service (e.g. 'Free trial signup', 'Client intake', 'Restaurant reservation')

  Exemple d'appel

  {"name": "generate_service_blueprint", "arguments": {"current": [], "service_name": "texte"}}

  Exemple de retour

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

• get_brand_principles≈ 258 tokens

  Get brand and visual-design principles — logo usage (clear space, min sizes, variants, placement, restraint), gradient usage (hierarchy, palette, contrast, trend vs signature), imagery (consistency, representation, purpose), visual hierarchy, and brand-as-system thinking. Use when the user asks about branding, logos, gradients, imagery, visual consistency, or how to treat a brand across surfaces.

  Paramètres, retour & exemple (2)

  Paramètres

  • topic · string · optionnel
    Filter by topic: 'logo', 'gradient', 'imagery', 'hierarchy', 'system', or a freeform search term. Omit to return all brand principles.
  • format · string · optionnel · full | checklist | brief
    Output format. Default: full.

  Exemple d'appel

  {"name": "get_brand_principles", "arguments": {"topic": "texte", "format": "full"}}

  Exemple de retour

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

• get_brand_system≈ 282 tokens

  Get a complete design system for building an app with branding like a specific company. Say 'Make me an app with branding like Spotify' and get the full token set, style guide, and implementation instructions. Matches against 12 known design systems and provides closest match with ready-to-use CSS.

  Paramètres, retour & exemple (3)

  Paramètres

  • mode · string · optionnel · light | dark
    Color mode preference. Default: based on the system's primary mode
  • format · string · optionnel · css | dtcg | guide
    Output format: 'css' for CSS variables, 'dtcg' for W3C tokens, 'guide' for full implementation guide. Default: guide
  • company · string · requis
    The company whose branding to use (e.g. 'Spotify', 'Stripe', 'Apple', 'Linear', 'Airbnb')

  Exemple d'appel

  {"name": "get_brand_system", "arguments": {"company": "texte"}}

  Exemple de retour

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

• get_brand_trends≈ 142 tokens

  Get current brand and visual-design trends — what's working in 2026 and where each trend fits or fails. Includes bento grids, monospace type, neon-on-dark-glass, generative patterns, brutalism rebound, AI-generated imagery, lowercase/mixed case. Each trend is time-stamped — treat as a calibration signal, not a prescription.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_brand_trends", "arguments": {}}

  Exemple de retour

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

• get_business_strategy≈ 196 tokens

  Get business and monetization strategies for digital products. Covers monetization models, retention strategies, onboarding optimization, growth mechanics, and product metrics frameworks.

  Paramètres, retour & exemple (2)

  Paramètres

  • type · string · requis
    Strategy type: monetization, retention, onboarding, growth, metrics
  • stage · string · optionnel · startup | growth | mature
    Company stage for contextual filtering

  Exemple d'appel

  {"name": "get_business_strategy", "arguments": {"type": "texte"}}

  Exemple de retour

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

• get_checklist≈ 250 tokens

  Get a pre-publish checklist for a specific UI type. Returns actionable yes/no items to verify before shipping.

  Paramètres, retour & exemple (2)

  Paramètres

  • type · string · requis
    What you're shipping (e.g. 'signup form', 'pricing page', 'dashboard', 'landing page', 'modal')
  • platform · string · optionnel · desktop | mobile | responsive | ios | react-native
    Platform context for platform-specific checks. 'ios' = native SwiftUI/iOS (Apple HIG); 'react-native' = RN/Expo (iOS HIG + Android Material: 44/48pt+hitSlop, accessibilityLabel/Role, font scaling, SafeAreaView, dark mode, platform parity, secrets). Both replace the web/mobile-web checks.

  Exemple d'appel

  {"name": "get_checklist", "arguments": {"type": "texte"}}

  Exemple de retour

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

• get_content_pattern≈ 172 tokens

  Get content design patterns — copy recipes for error messages, empty-state copy, notifications, and form validation. Returns do's, don'ts, good/bad examples, evidence, and a checklist.

  Paramètres, retour & exemple (1)

  Paramètres

  • type · string · requis · error-messages | empty-state-copy | notifications | form-validation
    Content pattern type

  Exemple d'appel

  {"name": "get_content_pattern", "arguments": {"type": "error-messages"}}

  Exemple de retour

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

• get_content_principles≈ 236 tokens

  Get UX-writing principles — clarity over cleverness, active voice, error-message anatomy, inclusive language, voice vs tone, and more. Filter by the writing context (e.g. 'error messages', 'notifications', 'form labels').

  Paramètres, retour & exemple (2)

  Paramètres

  • format · string · optionnel · full | checklist | brief
    Output format: full (all details), checklist (implications + violations), brief (just summary). Default: full
  • context · string · optionnel
    What you're writing for (e.g. 'error messages', 'onboarding copy', 'empty state', 'notification'). Omit to get all UX-writing principles.

  Exemple d'appel

  {"name": "get_content_principles", "arguments": {"format": "full", "context": "texte"}}

  Exemple de retour

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

• get_content_system≈ 225 tokens

  Get a brand's content design system — voice attributes, tone shifts by context, vocabulary (use/avoid/never), grammar rules, content patterns for errors/empty-states/buttons/etc., and inclusive language guidance.

  Paramètres, retour & exemple (2)

  Paramètres

  • id · string · requis
    Content system ID (e.g. 'conversational-product-voice', 'gov-uk', 'shopify-polaris', 'atlassian')
  • section · string · optionnel · all | voice | tone_shifts | vocabulary | grammar | content-patterns | inclusive-language
    Return just one section. Default: all.

  Exemple d'appel

  {"name": "get_content_system", "arguments": {"id": "texte"}}

  Exemple de retour

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

• get_d4d_framework≈ 177 tokens

  Get the Design for Delight (D4D) framework templates. Returns customer problem statement, ideal state, hypothesis, LOFA, and experiment templates for structured product thinking.

  Paramètres, retour & exemple (1)

  Paramètres

  • stage · string · optionnel · frame | empathy | broad | narrow | experiment | recommendation | full
    Which stage of the D4D loop to return. Default: full (all stages)

  Exemple d'appel

  {"name": "get_d4d_framework", "arguments": {"stage": "frame"}}

  Exemple de retour

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

• get_design_system≈ 233 tokens

  Get design tokens for a specific design system. Returns colors, typography, spacing, radii, elevation, and motion tokens in W3C DTCG, CSS custom properties, or flat format.

  Paramètres, retour & exemple (3)

  Paramètres

  • id · string · requis
    Design system ID (e.g. 'stripe', 'linear')
  • group · string · optionnel
    Filter to a token group: color, color-dark, color-light, typography, spacing, radius, elevation, motion
  • format · string · optionnel · dtcg | css | flat
    Output format: dtcg (W3C standard), css (custom properties), flat (key-value). Default: dtcg

  Exemple d'appel

  {"name": "get_design_system", "arguments": {"id": "texte"}}

  Exemple de retour

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

• get_metrics_framework≈ 215 tokens

  Get a product-metrics framework — HEART (Google), AARRR/Pirate (Dave McClure), North Star Metric, Conversion Funnel, RICE Scoring, or OKRs. Returns structure, when-to-use, pitfalls, and examples. Use when the user asks 'how should we measure success?' or 'what metrics should we track?'

  Paramètres, retour & exemple (2)

  Paramètres

  • id · string · optionnel
    Framework id (heart, aarrr, north-star-metric, conversion-funnel, rice-scoring, okrs). Omit to list all.
  • search · string · optionnel
    Search for a framework by name or summary.

  Exemple d'appel

  {"name": "get_metrics_framework", "arguments": {"id": "texte", "search": "texte"}}

  Exemple de retour

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

• get_pattern≈ 284 tokens

  Get proven UI/UX patterns for a specific design type. Returns do's, don'ts, evidence, and checklists for signup flows, pricing pages, navigation, forms, landing pages, dashboards, modals, empty states, error states, loading states, CTAs, social proof, and mobile conversion.

  Paramètres, retour & exemple (3)

  Paramètres

  • goal · string · optionnel · conversion | usability | accessibility | delight
    Filter by primary goal
  • type · string · requis
    Pattern type (e.g. 'signup-flow', 'pricing-page', 'navigation', 'forms', 'landing-page', 'dashboard', 'modals-dialogs', 'empty-states', 'error-states', 'loading-states', 'cta', 'social-proof', 'mobile-conversion')
  • platform · string · optionnel · desktop | mobile | responsive
    Filter patterns by platform context

  Exemple d'appel

  {"name": "get_pattern", "arguments": {"type": "texte"}}

  Exemple de retour

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

• get_principles≈ 404 tokens

  Get design principles relevant to a UI context. Returns usability heuristics, laws of UX, Gestalt principles, accessibility requirements, typography rules, and color theory — matched to what you're designing.

  Paramètres, retour & exemple (4)

  Paramètres

  • format · string · optionnel · full | checklist | brief
    Output format: full (all details), checklist (implications + violations), brief (just summary). Default: full
  • context · string · requis
    What you're designing (e.g. 'signup form', 'pricing page', 'mobile nav', 'dark dashboard')
  • category · string · optionnel
    Filter to category: accessibility, brand, color-systems, color-theory, component-architecture, d4d, gestalt, laws-of-ux, mobile-ux, nielsen-heuristics, research, responsive-layout, service-design, spacing-systems, typography, ux-writing
  • platform · string · optionnel · web | ios | react-native
    Platform context. 'ios' returns Apple HIG principles (Dynamic Type, 44pt targets, SF Symbols, safe areas, dark-mode, haptics, App Review privacy); 'react-native' returns RN principles (44/48pt+hitSlop, accessibilityLabel/Role, font scaling, SafeAreaView, dark mode, iOS+Android parity, secrets). Both replace the web/CSS-oriented set. Default: web.

  Exemple d'appel

  {"name": "get_principles", "arguments": {"context": "texte"}}

  Exemple de retour

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

• get_research_method≈ 246 tokens

  Get research method details — qualitative (interviews, contextual inquiry, diary, field, intercept), quantitative (surveys, analytics, A/B tests, benchmarking, clickstream), or usability (moderated, unmoderated, 5-second, card sort, tree test, heuristic eval). Returns specific protocols, do/don't guidance, evidence, and a checklist. Use when the user is designing a study or asking how to measure something.

  Paramètres, retour & exemple (2)

  Paramètres

  • search · string · optionnel
    Search within methods by name or description.
  • category · string · optionnel · qualitative | quantitative | usability | all
    Which family of methods. Default: all.

  Exemple d'appel

  {"name": "get_research_method", "arguments": {"search": "texte", "category": "qualitative"}}

  Exemple de retour

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

• get_service_pattern≈ 214 tokens

  Get a service design pattern — service blueprinting, human handoff, signup-as-service, omnichannel continuity, or moments of truth / recovery. Returns patterns, do/don't guidance, evidence, and a checklist. Use when the user is designing a service flow, escalation, cross-channel experience, or moment of truth.

  Paramètres, retour & exemple (1)

  Paramètres

  • type · string · requis · service-blueprinting | human-handoff | signup-as-service | omnichannel-continuity | moments-of-truth
    Service design pattern type

  Exemple d'appel

  {"name": "get_service_pattern", "arguments": {"type": "service-blueprinting"}}

  Exemple de retour

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

• get_service_standard≈ 126 tokens

  Get the GOV.UK Service Standard — 14 points the UK government uses to assess whether a public service is ready to launch. Widely applicable as a rigorous service-quality checklist beyond government. Use when the user asks how to evaluate a whole service.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_service_standard", "arguments": {}}

  Exemple de retour

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

• list_content_systems≈ 181 tokens

  Browse available content design systems — brand voice and tone guides (Conversational Product Voice, GOV.UK, Shopify Polaris, Atlassian). Filter by category or search by name.

  Paramètres, retour & exemple (2)

  Paramètres

  • search · string · optionnel
    Search by name, description, or tag
  • category · string · optionnel
    Filter by category: commerce-saas, government, marketing-saas, productivity-saas

  Exemple d'appel

  {"name": "list_content_systems", "arguments": {"search": "texte", "category": "texte"}}

  Exemple de retour

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

• list_creative_models≈ 205 tokens

  Browse Raven's provider-agnostic creative model catalog. These are capability slots for image, video, 3D, audio, character consistency, and creative analysis. Each entry lists typical inputs and best-for guidance.

  Paramètres, retour & exemple (2)

  Paramètres

  • capability · string · optionnel
    Filter by capability, e.g. product-photoshoot, text-to-video, brand-kit, ugc-ad.
  • media_type · string · optionnel · image | video | audio | 3d | campaign | analysis
    Filter by media type.

  Exemple d'appel

  {"name": "list_creative_models", "arguments": {"capability": "texte", "media_type": "image"}}

  Exemple de retour

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

• list_creative_presets≈ 176 tokens

  Browse Raven creative presets for product photoshoots, marketplace cards, UGC ads, TV spots, cinematic reveals, social launch packs, storyboards, and infographics.

  Paramètres, retour & exemple (2)

  Paramètres

  • search · string · optionnel
    Search preset name or description.
  • media_type · string · optionnel · image | video | campaign
    Filter presets by media type.

  Exemple d'appel

  {"name": "list_creative_presets", "arguments": {"search": "texte", "media_type": "image"}}

  Exemple de retour

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

• list_design_systems≈ 192 tokens

  Browse available design systems for tokens. Filter by category (component-library, consumer, developer, fintech, framework, platform, productivity) or search by name.

  Paramètres, retour & exemple (2)

  Paramètres

  • search · string · optionnel
    Search by name or description
  • category · string · optionnel
    Filter by category: component-library, consumer, developer, fintech, framework, platform, productivity. Saved user systems list under 'user'.

  Exemple d'appel

  {"name": "list_design_systems", "arguments": {"search": "texte", "category": "texte"}}

  Exemple de retour

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

• score_creative≈ 276 tokens

  Score a creative prompt, script, or ad concept for hook strength, benefit clarity, product signal, call-to-action, channel fit, audience fit, and brand fit. This is a transparent heuristic, not a proprietary prediction model. Local brand profiles are not available on the hosted (remote) endpoint (per-user state is a later phase). Omit 'brand_profile_id' to score the pasted creative statelessly.

  Paramètres, retour & exemple (4)

  Paramètres

  • channel · string · optionnel
    Target channel.
  • audience · string · optionnel
    Target audience if not in a brand profile.
  • creative_text · string · requis
    Prompt, script, ad copy, or creative concept to score.
  • brand_profile_id · string · optionnel
    Local Raven brand profile ID.

  Exemple d'appel

  {"name": "score_creative", "arguments": {"creative_text": "texte"}}

  Exemple de retour

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

• score_page≈ 405 tokens

  Score an HTML/CSS page across 7 design categories (Structure, Typography, Color & palette, Spacing & rhythm, Accessibility, Responsive layout, Design tokens), each rated 0–10. Scores are derived deterministically from the same checks as audit_page — no browser required. Pass html directly; the url argument is REJECTED on this hosted (remote) endpoint. Also returns the same overall 0–100 score and A–D grade audit_page produces, the weakest category, and the three categories Raven does not mechanically assess (brand, conversion, motion) with guidance on which tools to use for those. score_page url-capture is disabled on the hosted (remote) endpoint. Pass the page HTML via the 'html' argument instead.

  Paramètres, retour & exemple (4)

  Paramètres

  • url · string · optionnel
    REJECTED on this hosted (remote) endpoint; pass html instead. (Local/stdio: Raven launches headless chromium, renders the page, and scores the RENDERED DOM.)
  • html · string · optionnel
    The full HTML content of the page to score.
  • strict · boolean · optionnel
    Strict mode — count warnings as failures in the overall score. Default: false.
  • containerMaxWidth · number · optionnel
    Your design system's canonical content-container width in px (e.g. 1152). Forwarded to the responsive/max-width check.

  Exemple d'appel

  {"name": "score_page", "arguments": {"url": "texte", "html": "texte", "strict": true, "containerMaxWidth": 1}}

  Exemple de retour

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

• search_knowledge≈ 201 tokens

  Search across all design principles, UI patterns, and business strategies. Use when you need to find specific guidance or don't know which category to look in.

  Paramètres, retour & exemple (2)

  Paramètres

  • layer · string · optionnel · principles | patterns | business | all
    Which layer to search: principles, patterns, business, or all (default)
  • query · string · requis
    Search term (e.g. 'touch targets', 'pricing psychology', 'color contrast')

  Exemple d'appel

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

  Exemple de retour

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

• suggest_contrast_fix≈ 372 tokens

  Given failing WCAG color pairs, return the MINIMAL color change that clears the target ratio. For each {fg,bg} pair, computes the smallest foreground adjustment (and an alternative background adjustment) that reaches AA/AAA — with the achieved ratio and direction. Feeds directly from audit_contrast's failing pairs: pass them here to get concrete passing values instead of brute-forcing colors by hand. Pure offline math.

  Paramètres, retour & exemple (2)

  Paramètres

  • level · string · optionnel · AA | AAA
    WCAG level when targetRatio is not given per-pair. Default AA.
  • pairs · array · optionnel
    Color pairs to remediate. Each: { selector?, fg, bg, fontPx?, bold?, targetRatio? }. fontPx/bold pick the large-text threshold; targetRatio overrides the level.

  Exemple d'appel

  {"name": "suggest_contrast_fix", "arguments": {"level": "AA", "pairs": []}}

  Exemple de retour

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

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://mcp.ravenmcp.ai/api/mcp