com.mcpqueen/registry

Est-ce que com.mcpqueen/registry est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.mcpqueen/registry » 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 7 outils

• get_server_grade≈ 324 tokens

  Get the full grade and verbatim probe evidence for one MCP server, by its official registry name (e.g. 'com.healthai/radar').

  Paramètres, retour & exemple (1)

  Paramètres

  • name · string · requis
    Registry server name

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"grade": "texte", "score": 1, "version": "texte", "evidence": "texte", "repo_url": "texte", "probed_at": "texte", "reachable": 1, "latency_ms": 1, "remote_url": "texte", "tool_count": 1, "description": "texte", "provisional": 1}}

• get_trust_receipt≈ 360 tokens

  Get one MCP server's complete evidence receipt: operational grade, deterministic security/data-integrity/citation/claim observations, and reviewed real-usage field reports. Missing observations are explicitly unaudited, never treated as a pass.

  Paramètres, retour & exemple (1)

  Paramètres

  • name · string · requis
    Official registry server name

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"server": {}, "audit_state": "observations_published", "observations": [], "evidence_page": "texte", "safety_notice": "texte", "interpretation": "texte", "trust_dimensions": [], "response_benchmarks": [], "reviewed_field_reports": []}}

• list_grades≈ 296 tokens

  List the top graded MCP servers from the mcpqueen registry (deterministic probe grades with evidence). Returns grade, score 0-100, latency, tool count and auth state per server.

  Paramètres, retour & exemple (1)

  Paramètres

  • limit · number · optionnel
    Max servers to return (default 25, max 100)

  Exemple d'appel

  {"name": "list_grades", "arguments": {"limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"results": [], "returned": 1, "safety_notice": "texte"}}

• search_servers≈ 628 tokens

  Search the MCP evidence registry using a natural multi-word task (e.g. 'reliable no-auth drug interaction server with citations'). Tokenizes and expands common synonyms, ranks metadata plus observed tool descriptions, and supports operational-grade/auth/latency/category filters. Use get_trust_receipt or search_trust_evidence for security, data, citation, claim, and response evidence.

  Paramètres, retour & exemple (6)

  Paramètres

  • auth · string · optionnel · any | open | required
    Filter by authentication state (default any)
  • limit · number · optionnel
    Max results (default 10, max 25)
  • query · string · requis
    Keyword or task to search name/title/description for
  • category · string · optionnel
    Optional category filter: Dev & Code, Data & Databases, Web & Search, AI & Agents, Finance & Crypto, Communication, Productivity, Security, Commerce, Media & Design, Cloud & Infra, Science & Health, Other
  • minimum_grade · string · optionnel · A | B | C | D | F
    Worst acceptable live grade
  • max_latency_ms · number · optionnel
    Maximum measured initialize latency in milliseconds

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"message": "texte", "results": [], "safety_notice": "texte", "feedback_reminder": "texte", "interpreted_terms": []}}

• search_tools≈ 651 tokens

  Search across the actual tools that graded MCP servers expose (their tool names and descriptions, captured live from tools/list) — not just server metadata. Use this when you need a specific capability or data type, e.g. 'get weather', 'query postgres', 'device recall', 'FDA 510k'. Returns the matching tools with the server that offers each, its grade, and the remote endpoint so you can connect directly.

  Paramètres, retour & exemple (6)

  Paramètres

  • auth · string · optionnel · any | open | required
    Filter by authentication state (default any)
  • limit · number · optionnel
    Max matching tools (default 15, max 40)
  • query · string · requis
    Capability, data type, or keyword to match against tool names and descriptions
  • category · string · optionnel
    Optional server-category filter: Dev & Code, Data & Databases, Web & Search, AI & Agents, Finance & Crypto, Communication, Productivity, Security, Commerce, Media & Design, Cloud & Infra, Science & Health, Other
  • minimum_grade · string · optionnel · A | B | C | D | F
    Worst acceptable live server grade
  • max_latency_ms · number · optionnel
    Maximum measured initialize latency in milliseconds

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"message": "texte", "results": [], "safety_notice": "texte", "feedback_reminder": "texte", "interpreted_terms": []}}

• search_trust_evidence≈ 476 tokens

  Search published MCP trust evidence and reviewed real-usage field reports. Use for questions such as which servers expose citations, have access caveats, make unverifiable corpus claims, or show security concerns. Returns verbatim observations with dates and source type, not a synthetic trust score.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · number · optionnel
    Max evidence items (default 20, max 50)
  • query · string · requis
    Evidence, claim, source, capability, caveat, or server keyword
  • status · string · optionnel · any | observed | pass | concern | unverified | not_testable
  • dimension · string · optionnel · any | security | data_integrity | citation_quality | claim_verification | field_report

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"query": "texte", "results": [], "returned": 1, "safety_notice": "texte", "interpretation": "texte"}}

• submit_feedback≈ 263 tokens

  Submit a field report about an MCP server you have actually used (what worked, what failed, surprising behavior). Reports are quarantined for human review and never auto-published.

  Paramètres, retour & exemple (3)

  Paramètres

  • report · string · requis
    The field report, 20-2000 chars, specific and factual
  • agent_name · string · optionnel
    Optional: which agent/client is reporting
  • server_name · string · requis
    Official registry name of the server the report is about

  Exemple d'appel

  {"name": "submit_feedback", "arguments": {"report": "texte", "server_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "texte", "message": "texte", "server_name": "texte", "safety_notice": "texte"}}

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://mcpqueen.com/mcp