io.verifymcp/mcp

Est-ce que io.verifymcp/mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.verifymcp/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 9 outils

• get_server≈ 2644 tokens

  Get the full VerifyMCP trust report for one MCP server: score with per-category verdicts and reasons, the tools it exposes with their context-token cost, and its recent change history. Use before installing or trusting a server. Accepts a package name, endpoint URL, registry name or verifymcp slug.

  Paramètres, retour & exemple (2)

  Paramètres

  • component · string · optionnel
    Which channel to report on when a server ships several.
  • identifier · string · requis
    Package name, endpoint URL, registry name or verifymcp slug.

  Exemple d'appel

  {"name": "get_server", "arguments": {"identifier": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"asOf": "texte", "count": 1, "items": [], "total": 1, "notice": "texte", "source": "texte", "truncated": true}}

• get_server_alternatives≈ 606 tokens

  Other MCP servers doing a similar job to a given one, with their trust scores. Neighbours share a product, publisher namespace or category; this is not a semantic search.

  Paramètres, retour & exemple (1)

  Paramètres

  • identifier · string · requis
    Package name, endpoint URL, registry name or verifymcp slug.

  Exemple d'appel

  {"name": "get_server_alternatives", "arguments": {"identifier": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"asOf": "texte", "count": 1, "items": [], "total": 1, "notice": "texte", "source": "texte", "truncated": true}}

• get_server_comparison≈ 976 tokens

  Compare up to 5 MCP servers side by side: trust scores, per-category breakdown, tool counts and context-token cost. Use when choosing between candidates that do the same job. Accepts package names, endpoint URLs, registry names or verifymcp slugs.

  Paramètres, retour & exemple (1)

  Paramètres

  • identifiers · array · requis
    Two to 5 servers to compare, as names, URLs or slugs.

  Exemple d'appel

  {"name": "get_server_comparison", "arguments": {"identifiers": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"asOf": "texte", "count": 1, "items": [], "total": 1, "notice": "texte", "source": "texte", "truncated": true}}

• get_server_diagnostics≈ 1477 tokens

  The evidence behind one server's score: TLS, DNSSEC, authorization, redirects, transports, provenance, install scripts, known CVEs and dependency health. Use to explain a low score.

  Paramètres, retour & exemple (2)

  Paramètres

  • component · string · optionnel
    Which channel to report on when a server ships several.
  • identifier · string · requis
    Package name, endpoint URL, registry name or verifymcp slug.

  Exemple d'appel

  {"name": "get_server_diagnostics", "arguments": {"identifier": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"asOf": "texte", "count": 1, "items": [], "total": 1, "notice": "texte", "source": "texte", "truncated": true}}

• get_server_install_config≈ 1310 tokens

  Ready-to-paste install snippets for one MCP server, for every client we support. An MCPB bundle has no launch command, so it returns the download URL, the registry's SHA-256 and commands to verify the file instead. Read get_server first: this returns configuration, not a safety judgement.

  Paramètres, retour & exemple (2)

  Paramètres

  • component · string · optionnel
    Which channel to report on when a server ships several.
  • identifier · string · requis
    Package name, endpoint URL, registry name or verifymcp slug.

  Exemple d'appel

  {"name": "get_server_install_config", "arguments": {"identifier": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"asOf": "texte", "count": 1, "items": [], "total": 1, "bundle": {}, "notice": "texte", "source": "texte", "context": {}, "truncated": true}}

• get_server_tools≈ 1193 tokens

  Every tool one MCP server exposes, with its parameters, output schema and context-token cost. Use when get_server reported the tool list was truncated.

  Paramètres, retour & exemple (2)

  Paramètres

  • component · string · optionnel
    Which channel to report on when a server ships several.
  • identifier · string · requis
    Package name, endpoint URL, registry name or verifymcp slug.

  Exemple d'appel

  {"name": "get_server_tools", "arguments": {"identifier": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"asOf": "texte", "count": 1, "items": [], "total": 1, "notice": "texte", "source": "texte", "truncated": true}}

• list_known_malware≈ 1060 tokens

  List MCP server components carrying a supply-chain malware finding. Use to check whether anything in the register is flagged before installing.

  Paramètres, retour & exemple (1)

  Paramètres

  • status · string · optionnel · active | unverified | cleared | all
    Which findings to return: active, unverified, cleared or all. Defaults to active.

  Exemple d'appel

  {"name": "list_known_malware", "arguments": {"status": "active"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"asOf": "texte", "count": 1, "items": [], "total": 1, "notice": "texte", "source": "texte", "truncated": true}}

• list_products≈ 520 tokens

  List the products MCP servers integrate with, such as github or notion, and how many servers cover each. Use to find the product slug that list_servers accepts.

  Paramètres, retour & exemple (1)

  Paramètres

  • query · string · optionnel
    Name fragment to match against product names and slugs.

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"asOf": "texte", "count": 1, "items": [], "total": 1, "notice": "texte", "source": "texte", "truncated": true}}

• list_servers≈ 1068 tokens

  Filter the VerifyMCP directory of scored MCP servers. Use to discover servers by name fragment, ecosystem, product or trust score. Name matching only: descriptions and capabilities are not searched, so a plain-English question matches nothing. Returns the first 100.

  Paramètres, retour & exemple (7)

  Paramètres

  • sort · string · optionnel · score_desc | score_asc | name_asc | name_desc | channels_asc | channels_desc
    Default: best match (then trust) with a query, else trust. A given sort is applied exactly.
  • query · string · optionnel
    Name fragment to match against server and package names.
  • types · array · optionnel
    Restrict to these ecosystems; a server matches any one of them.
  • scored · string · optionnel · scored | unscored | all
    Include unscored servers. Defaults to scored only.
  • product · string · optionnel
    Restrict to servers classified as working with this product, e.g. github.
  • maxScore · integer · optionnel
    Highest trust score to include.
  • minScore · integer · optionnel
    Lowest trust score to include.

  Exemple d'appel

  {"name": "list_servers", "arguments": {"sort": "score_desc", "query": "texte", "types": [], "scored": "scored", "product": "texte", "maxScore": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"asOf": "texte", "count": 1, "items": [], "total": 1, "notice": "texte", "source": "texte", "truncated": true}}

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.verifymcp.io