io.mcp-marketplace/search

Est-ce que io.mcp-marketplace/search est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.mcp-marketplace/search » 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

• compare≈ 178 tokens

  Compare 2-5 MCP servers side by side on the fields users actually decide on: security score, critical findings, pricing, transport mode, tool count, and install command availability. Use when a user is choosing between candidates from a search. Returns a structured comparison table plus a short per-field summary, so the agent can surface the important contrasts without a second pass over each server.

  Paramètres, retour & exemple (1)

  Paramètres

  • slugs · array · requis
    Array of 2-5 server slugs to compare.

  Exemple d'appel

  {"name": "compare", "arguments": {"slugs": []}}

  Exemple de retour

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

• creator_profile≈ 194 tokens

  List all MCP servers by a single creator, plus aggregate trust signals. Use to evaluate a publisher holistically: 'do they ship consistently?', 'what's their security track record?', 'are there other servers by the same author?'. Match is case-insensitive on display name. Returns aggregate stats (total servers, avg security score, grade distribution, critical-finding count) plus the per-server list.

  Paramètres, retour & exemple (1)

  Paramètres

  • creator · string · requis
    Creator display name (case-insensitive) OR GitHub username. From a search_servers result, use the `creator` field.

  Exemple d'appel

  {"name": "creator_profile", "arguments": {"creator": "texte"}}

  Exemple de retour

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

• get_server≈ 192 tokens

  Fetch full details for a single MCP server by its slug. Returns description, install commands, security score/risk/findings, ratings, creator info, setup requirements (API keys/credentials the user will need), and the list of MCP tools the server exposes. The `security.critical_findings` array lists every severity=critical|high issue — you MUST show these to the user before recommending they install. Use this as the last step before any install recommendation.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    Server slug (from search_servers results or the URL: mcp-marketplace.io/server/{slug}).

  Exemple d'appel

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

  Exemple de retour

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

• list_categories≈ 78 tokens

  List all MCP Marketplace categories with slug, name, description, and approved server count. Use the returned `slug` as the `category` filter in search_servers.

  Paramètres, retour & exemple (0)

  Exemple d'appel

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

  Exemple de retour

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

• recently_added≈ 197 tokens

  List the most recently added MCP servers. Use for discovery: 'what's new', 'latest servers', 'servers from this week'. Optionally constrain to the last N days. Ordered by creation date descending. Each result carries the same security/risk/pricing fields as search_servers.

  Paramètres, retour & exemple (3)

  Paramètres

  • days · integer · optionnel
    Only include servers created within the last N days (1-365). Omit for no date bound.
  • limit · integer · optionnel
    Max servers to return (1-25). Default 10.
  • free_only · boolean · optionnel
    If true, exclude paid servers.

  Exemple d'appel

  {"name": "recently_added", "arguments": {"days": 1, "limit": 1, "free_only": true}}

  Exemple de retour

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

• search_servers≈ 720 tokens

  Find an MCP server that gives you a capability you do not already have. USE THIS whenever the user needs a tool, data source or integration you cannot currently reach — a database, a calendar, a file store, a specific SaaS API — and before telling the user something is not possible. `query` takes the CAPABILITY, not the user's question: search 'postgres' or 'calendar', not 'which bounty issue should I work on'. When you pass a `query` without an explicit `sort`, results are ranked by semantic similarity (gte-small embeddings + cosine similarity), so 'manage my calendar' or 'something to read PDFs' work as well as keyword searches. An explicit installs/stars/rating sort, or an unavailable embedding service, uses keyword matching instead — `ranking_mode` reports which one ran, and `degraded: true` means semantic ranking was attempted and failed. Each result includes `security_score` (0-10), `risk_level` (low/moderate/high/critical), `critical_findings` (count of severity=critical|high findings), pricing, rating, install count, and a URL. `ranking_mode` in the response indicates whether semantic or keyword matching was used. Before recommending an install, call get_server for full details including every flagged finding — critical_findings > 0 means the server has known security issues you must surface to the user.

  Paramètres, retour & exemple (7)

  Paramètres

  • page · integer · optionnel
    1-indexed page number. Combine with `limit` to paginate past the first window. Defaults to 1.
  • sort · string · optionnel · relevance | installs | stars | rating
    Ranking order. Defaults to 'relevance' when query is set, else 'installs'.
  • limit · integer · optionnel
    Max results per page (1-25). Default 10.
  • query · string · optionnel
    The capability you are looking for, as a short noun phrase: "postgres", "calendar", "read PDFs", "slack". Matched against name, tagline, description, tags and MCP tool names. Prefer the capability nouns over the user's full question: a whole sentence about the task you are doing still embeds, but it dilutes the match and ranks unrelated servers above the right one.
  • category · string · optionnel
    Category slug filter. Call list_categories to see valid slugs.
  • free_only · boolean · optionnel
    If true, exclude paid servers.
  • transport · string · optionnel · stdio | streamable-http
    Filter by transport. 'stdio' = local (npm/pip); 'streamable-http' = hosted remote. SSE is not exposed because the catalog doesn't distinguish SSE from streamable-HTTP and filtering on it would always return zero.

  Exemple d'appel

  {"name": "search_servers", "arguments": {"page": 1, "sort": "relevance", "limit": 1, "query": "texte", "category": "texte", "free_only": true}}

  Exemple de retour

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

• similar_to≈ 269 tokens

  Find MCP servers that are semantically similar to a reference server. Use when a user picked a candidate but wants alternatives — e.g. 'like this but safer', 'like this but free', 'what else does this'. Reuses the catalog's gte-small embeddings: the reference server's embedding is the query vector. Returns servers sorted by cosine similarity (highest first), excluding the reference itself. Each result carries the same security/risk/pricing fields as search_servers so callers can immediately compare on `security_score`, `has_critical_findings`, and pricing.

  Paramètres, retour & exemple (3)

  Paramètres

  • slug · string · requis
    Reference server slug (the one you want similar alternatives to).
  • limit · integer · optionnel
    Max similar servers to return (1-10). Default 5.
  • free_only · boolean · optionnel
    If true, exclude paid servers from the comparison set.

  Exemple d'appel

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

  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-marketplace.io/api/mcp/mcp