com.aidemos/catalogue

Est-ce que com.aidemos/catalogue est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.aidemos/catalogue » 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 17 outils

• answer≈ 336 tokens

  ANSWER a buyer question in ONE call: which tool is best at a specific capability, with proof. Returns the resolved verdict our testing team's evidence supports — a named winner FOR THE ASKED CRITERION, every tested tool ranked with a comparable score /5, the CONDITIONS each result holds under (e.g. 'clean tables yes; nested headers no'), dissenting observations preserved as openable links, the tie-break reason, and artifact proof URLs. Answers are materialized from the evidence substrate — the same question returns the same answer. Honestly refuses (coverage: not_tested) when we never tested the topic. Start HERE for any 'which tool is best at X' / 'A or B for X' question; use get_evidence for the raw cells behind it.

  Paramètres, retour & exemple (4)

  Paramètres

  • ranking · string · optionnel
    Ranking slug (skips routing).
  • question · string · optionnel
    The buyer question in natural language, e.g. 'Which document extraction tool best preserves table structure from scanned PDFs?'. Alternative: pass ranking + criterion explicitly.
  • scenario · string · optionnel
    Optional scenario/condition of interest.
  • criterion · string · optionnel
    Criterion slug or exact name (with `ranking`).

  Exemple d'appel

  {"name": "answer", "arguments": {"ranking": "texte", "question": "texte", "scenario": "texte", "criterion": "texte"}}

  Exemple de retour

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

• compare_tools≈ 184 tokens

  Evidence-aligned comparison of two tools, honesty enforced structurally: head_to_head (cells from the SAME test input — provable same-input comparison), related_not_same_input (same dimension, different runs — flagged), and each tool's unique evidence. Built from real observation cells with artifacts, not prose.

  Paramètres, retour & exemple (3)

  Paramètres

  • tool_a · string · requis
    First tool slug, e.g. "llamaparse".
  • tool_b · string · requis
    Second tool slug, e.g. "landing-ai".
  • criterion · string · optionnel
    Optional: restrict to one criterion.

  Exemple d'appel

  {"name": "compare_tools", "arguments": {"tool_a": "texte", "tool_b": "texte"}}

  Exemple de retour

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

• get_evidence≈ 359 tokens

  Query the evidence graph: observation cells (tool × test-scenario × criterion) → verdict, score, the researcher's note, and the REAL artifacts (input/output screenshots) that prove it. The ground truth behind every ranking — filter any combination of tool(s), scenario (slug, group tag, or name), criterion, verdict, or evidence state. evidence_state: "verified" = artifact-backed, "observed" = noted without artifact, "scored-only" = number only.

  Paramètres, retour & exemple (8)

  Paramètres

  • tool · string · optionnel
    Tool slug or name, e.g. "landing-ai".
  • limit · integer · optionnel
    Max cells (default 50).
  • tools · array · optionnel
    Several tools at once.
  • ranking · string · optionnel
    Ranking page slug — scope cells to the evidence run that published ranking is bound to (exactly what the page renders).
  • verdict · string · optionnel · worked | mixed | struggled | failed
  • evidence · string · optionnel · verified | observed | scored-only
  • scenario · string · optionnel
    Scenario slug, cross-run group tag (e.g. "scanned-research-paper"), or name fragment.
  • criterion · string · optionnel
    Criterion slug or name, e.g. "table extraction".

  Exemple d'appel

  {"name": "get_evidence", "arguments": {"tool": "texte", "limit": 1, "tools": [], "ranking": "texte", "verdict": "worked", "evidence": "verified"}}

  Exemple de retour

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

• get_persona≈ 104 tokens

  Given a persona slug (from list_personas), return everything tagged with it: persona, use_cases[], rankings[], compares[], toolkits[], tools[]. Mirrors a persona landing page.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    Persona slug, e.g. "students".

  Exemple d'appel

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

  Exemple de retour

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

• get_ranking≈ 461 tokens

  Full ranking detail as a JSON+Markdown envelope: ranked tools (rank/badge/scores), criteria, winner, breakdown (JSON) + verdicts / final take (Markdown). Every ranked tool carries `proof`: real artifact URLs from the exact evidence run this page is bound to, each with the /evidence permalink for the finding it proves — verdict and proof arrive together, no second call needed to cite evidence. `proof.artifact_count` is the true total and `proof.all_findings` is the get_evidence call that returns all of it. null if unknown. Pass `fields` to project to only the keys you need (token-efficient).

  Paramètres, retour & exemple (3)

  Paramètres

  • slug · string · requis
    Ranking slug, e.g. "resume-parsing-api" (from list_rankings).
  • proof · string · optionnel · sample | full | none
    How many proof artifacts to inline. "sample" (default) = up to 6 per tool, spread across distinct criteria so you see breadth; "full" = every artifact; "none" = counts only, no URLs. Counts (artifact_count / finding_count) are the TRUE totals in every mode, so you can always tell what you did not receive.
  • fields · array · optionnel
    Optional projection: return ONLY these top-level fields (identity id/name/title/slug/url is always included) to control response size. Available: id, title, slug, url, abstract, read_time, tested_date, category, use_case, personas, tags, winner, methodology, tools, breakdown, final_take, evidence_run.

  Exemple d'appel

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

  Exemple de retour

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

• get_tool≈ 482 tokens

  Full tool detail as a JSON+Markdown envelope: identity, pricing, per-feature scores, fit, FAQ, relationships (JSON) + our_take / in-depth review (Markdown). Includes `proof`: real artifact URLs (input/output screenshots, recordings) from the runs that tested it, each with the /evidence permalink for the finding it proves — you can cite evidence from THIS call. null if unknown. Pass `fields` to project to only the keys you need (token-efficient).

  Paramètres, retour & exemple (3)

  Paramètres

  • slug · string · requis
    Tool seo_slug, e.g. "affinda" (from list_tools).
  • proof · string · optionnel · sample | full | none
    How many proof artifacts to inline. "sample" (default) = up to 6 per tool, spread across distinct criteria so you see breadth; "full" = every artifact; "none" = counts only, no URLs. Counts (artifact_count / finding_count) are the TRUE totals in every mode, so you can always tell what you did not receive.
  • fields · array · optionnel
    Optional projection: return ONLY these top-level fields (identity id/name/title/slug/url is always included) to control response size. Available: id, name, slug, url, heading, website, domain, category, sub_category, content_type, personas, tags, rating, testing_history, features, pricing, fit, use_case_track_record, related_pages, related_reads, similar_tools, faq, demo_video, our_take, in_depth_review_md, proof.

  Exemple d'appel

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

  Exemple de retour

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

• get_use_case≈ 251 tokens

  Full use-case detail as a JSON+Markdown envelope: step guide, pros/cons, FAQ, tools used (JSON) + the full narrative guide (Markdown, full_md). null if unknown. Pass `fields` to project to only the keys you need (token-efficient).

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Use-case slug (from list_use_cases).
  • fields · array · optionnel
    Optional projection: return ONLY these top-level fields (identity id/name/title/slug/url is always included) to control response size. Available: id, title, slug, url, abstract, read_time, category, audience, personas, tags, tools_used, step_guide, what_to_expect, faq, full_md.

  Exemple d'appel

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

  Exemple de retour

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

• list_categories≈ 63 tokens

  List the category vocabulary in use with per-type counts and a source flag ("collection"|"derived"), sorted by total.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_categories", "arguments": {}}

  Exemple de retour

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

• list_compares≈ 113 tokens

  List published head-to-head comparison pages: id, title, slug, url, tool_a, tool_b, personas[], shared_use_cases[], updated_at.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Max items to return. Omit for all.
  • offset · integer · optionnel
    Items to skip (paging).

  Exemple d'appel

  {"name": "list_compares", "arguments": {"limit": 1, "offset": 1}}

  Exemple de retour

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

• list_personas≈ 68 tokens

  List personas with published-page counts per type {use_cases, rankings, tools, compares, toolkits}. The slugs are valid input for get_persona.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_personas", "arguments": {}}

  Exemple de retour

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

• list_rankings≈ 116 tokens

  List published ranking pages ("best X"): id, title, slug, url, use_case, persona, category, tools_count, winner, tested_as_of, updated_at.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Max items to return. Omit for all.
  • offset · integer · optionnel
    Items to skip (paging).

  Exemple d'appel

  {"name": "list_rankings", "arguments": {"limit": 1, "offset": 1}}

  Exemple de retour

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

• list_toolkits≈ 101 tokens

  List published toolkit pages (curated bundles): id, title, slug, url, category.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Max items to return. Omit for all.
  • offset · integer · optionnel
    Items to skip (paging).

  Exemple d'appel

  {"name": "list_toolkits", "arguments": {"limit": 1, "offset": 1}}

  Exemple de retour

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

• list_tools≈ 102 tokens

  List published AI tool pages: id, name, slug, url, domain, personas[], categories[].

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Max items to return. Omit for all.
  • offset · integer · optionnel
    Items to skip (paging).

  Exemple d'appel

  {"name": "list_tools", "arguments": {"limit": 1, "offset": 1}}

  Exemple de retour

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

• list_use_cases≈ 106 tokens

  List published use-case pages (how-to guides): id, title, slug, url, persona, category, updated_at.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Max items to return. Omit for all.
  • offset · integer · optionnel
    Items to skip (paging).

  Exemple d'appel

  {"name": "list_use_cases", "arguments": {"limit": 1, "offset": 1}}

  Exemple de retour

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

• rankings_for_tool≈ 92 tokens

  Given a tool id, return the tool {id,name,slug} and every ranking it appears in [{id,title,slug,url,use_case,rank,badge}].

  Paramètres, retour & exemple (1)

  Paramètres

  • tool_id · string|integer · requis
    Tool id (from list_tools).

  Exemple d'appel

  {"name": "rankings_for_tool", "arguments": {"tool_id": 1}}

  Exemple de retour

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

• search≈ 305 tokens

  Search the published catalogue across use cases, rankings, tools, comparisons, and toolkits. Returns ranked light refs [{ kind, id, title, slug, url, snippet, score, meta }] — then call get_tool / get_ranking / get_use_case for full detail. `mode`: keyword (substring), semantic (meaning, via embeddings — finds pages by what they cover), or hybrid (default, fuses both). Optional filters: type[], persona, category.

  Paramètres, retour & exemple (6)

  Paramètres

  • mode · string · optionnel · keyword | semantic | hybrid
    Search mode.
  • type · array · optionnel
    Restrict to these kinds (default: all).
  • limit · integer · optionnel
    Max results (default 20).
  • query · string · requis
    Free-text search query.
  • persona · string · optionnel
    Restrict to items tagged with this persona slug.
  • category · string · optionnel
    Restrict to this category (case-insensitive).

  Exemple d'appel

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

  Exemple de retour

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

• tools_in_ranking≈ 103 tokens

  Given a ranking id, return the ranking {id,title,slug} and its ranked tools [{id,name,slug,url,rank,badge}] (badge: Best/Usable/Needs work/Unstable/Failed).

  Paramètres, retour & exemple (1)

  Paramètres

  • ranking_id · string|integer · requis
    Ranking id (from list_rankings).

  Exemple d'appel

  {"name": "tools_in_ranking", "arguments": {"ranking_id": 1}}

  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.aidemos.com/mcp