dev.contextfetch/mcp

Est-ce que dev.contextfetch/mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « dev.contextfetch/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 13 outils

• contextfetch_answer≈ 192 tokens

  Answer a question with passages quoted verbatim from the web, never generated: searches, scores every passage of the top pages with a cross-encoder and returns the best ones with [n] citations to their sources. Use it for quick factual lookups; the quotes may not fully answer an open-ended question. Costs 1 credit.

  Paramètres, retour & exemple (2)

  Paramètres

  • query · string · requis
    The question.
  • num_results · integer · optionnel
    Pages searched for passages (1-10, default 5).

  Exemple d'appel

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

  Exemple de retour

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

• contextfetch_auto_reload≈ 263 tokens

  Turn auto-reload on or off, or change it: when credits drop below `threshold`, the saved card buys `pack` again, up to `monthly_max_usd` per month. Needs an API key and a card saved at checkout. The monthly cap cannot be raised above $500 here.

  Paramètres, retour & exemple (4)

  Paramètres

  • pack · string · optionnel · instant | builder | scale
    Pack to buy: instant $15/15,000, builder $50/60,000, scale $150/200,000.
  • enabled · boolean · requis
    true to turn auto-reload on, false to turn it off.
  • threshold · integer · optionnel
    Reload when credits drop below this (100-100,000, default 1,000).
  • monthly_max_usd · number · optionnel
    Monthly spending cap in USD (at most 500).

  Exemple d'appel

  {"name": "contextfetch_auto_reload", "arguments": {"enabled": true}}

  Exemple de retour

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

• contextfetch_balance≈ 100 tokens

  Show the API key's remaining credits, daily burn rate (7-day average) and auto-reload settings, including the last auto-reload error if a payment failed. Needs an API key (Authorization: Bearer); free.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "contextfetch_balance", "arguments": {}}

  Exemple de retour

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

• contextfetch_crawl≈ 326 tokens

  Crawl one website from a start URL and get its pages as Markdown: same-site links only, up to `max_depth` hops (<= 3) and `limit` pages (<= 50). Pass `query` to rank the pages by relevance and return only their relevant passages. Costs 1 credit per page returned.

  Paramètres, retour & exemple (6)

  Paramètres

  • url · string · requis
    Public http(s) start URL.
  • limit · integer · optionnel
    Maximum pages to return (1-50, default 10).
  • query · string · optionnel
    Optional topic: ranks pages and prunes each to the relevant passages.
  • max_depth · integer · optionnel
    Link hops from the start page (0-3, default 1).
  • exclude_paths · array · optionnel
    Regexes; never follow links whose path matches one.
  • include_paths · array · optionnel
    Regexes; only follow links whose path matches one, e.g. ["^/docs/"].

  Exemple d'appel

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

  Exemple de retour

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

• contextfetch_deep_research≈ 317 tokens

  Same as contextfetch_research (kept for existing clients): up to 3 sub-queries run server-side, sources deduped and ranked against the question, one Markdown evidence pack with numbered sources and query-pruned passages. Each sub-query is one search and costs 1 credit. You SHOULD pass your own `sub_queries` (up to 3 distinct angles on the question) for better coverage. If omitted, they are derived from `query`: the query itself, query + "documentation", and query + "benchmark" when it asks about speed, performance or comparisons, else query + "example".

  Paramètres, retour & exemple (3)

  Paramètres

  • query · string · requis
    The research question.
  • sub_queries · array · optionnel
    Up to 3 search queries covering different angles of the question. Strongly recommended.
  • num_results_per_query · integer · optionnel
    Results per sub-query (1-25, default 5; at most 10 are used).

  Exemple d'appel

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

  Exemple de retour

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

• contextfetch_extract_url≈ 159 tokens

  Fetch a public web page (docs, articles, GitHub files, arXiv papers) as clean Markdown with tables preserved. Pass `query` to get only the passages relevant to it instead of the whole page.

  Paramètres, retour & exemple (2)

  Paramètres

  • url · string · requis
    Public http(s) URL to read.
  • query · string · optionnel
    Optional question or topic; returns only the relevant passages.

  Exemple d'appel

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

  Exemple de retour

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

• contextfetch_find_similar≈ 166 tokens

  Find pages similar to a given URL (alternatives, related docs, competing libraries), excluding the source domain. Returns titles, URLs and the most relevant passages as Markdown.

  Paramètres, retour & exemple (2)

  Paramètres

  • url · string · requis
    Public http(s) URL to find similar pages for.
  • num_results · integer · optionnel
    Number of results to return (1-25, default 5).

  Exemple d'appel

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

  Exemple de retour

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

• contextfetch_get_free_key≈ 108 tokens

  Get a free ContextFetch API key (no signup, no payment) with starter credits, for when the keyless daily limit runs out. One key per network, ever: keep the key it returns and use it as `Authorization: Bearer <key>`.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "contextfetch_get_free_key", "arguments": {}}

  Exemple de retour

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

• contextfetch_map≈ 261 tokens

  List a website's URLs without fetching its pages: its sitemaps (from robots.txt, else /sitemap.xml) plus the start page's links, same site only, up to `limit` (<= 5,000). Use it to find the right pages before contextfetch_extract_url or contextfetch_crawl. Costs 1 credit.

  Paramètres, retour & exemple (4)

  Paramètres

  • url · string · requis
    Public http(s) URL of the site (any page on it).
  • limit · integer · optionnel
    Maximum URLs (1-5,000, default 100).
  • exclude_paths · array · optionnel
    Regexes; never list URLs whose path matches one.
  • include_paths · array · optionnel
    Regexes; only list URLs whose path matches one, e.g. ["^/blog/"].

  Exemple d'appel

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

  Exemple de retour

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

• contextfetch_research≈ 316 tokens

  Research a question in one call, server-side: runs up to 5 web searches (sub-queries) concurrently, dedupes the pages by URL, ranks them all against the question with a cross-encoder and returns one Markdown evidence pack with numbered [n] sources and their query-pruned passages, quoted verbatim (no generated text). Costs 1 credit per sub-query. Pass your own `sub_queries` (distinct angles on the question) for better coverage; if omitted they are derived from `query`: the query, query + "documentation", and query + "benchmark" (speed or comparison questions) or + "example".

  Paramètres, retour & exemple (3)

  Paramètres

  • query · string · requis
    The research question.
  • sub_queries · array · optionnel
    Up to 5 search queries covering different angles of the question. Recommended.
  • num_results_per_query · integer · optionnel
    Results per sub-query (1-10, default 5).

  Exemple d'appel

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

  Exemple de retour

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

• contextfetch_search≈ 252 tokens

  Search the web and get LLM-ready Markdown. Each result has its title, URL and only the passages relevant to the query (cross-encoder pruned context), so it costs far fewer tokens than raw pages. Use for current events, documentation, APIs, research and fact checking.

  Paramètres, retour & exemple (4)

  Paramètres

  • query · string · requis
    Natural-language search query.
  • num_results · integer · optionnel
    Number of results to return (1-25, default 5).
  • exclude_domains · array · optionnel
    Never return results from these domains.
  • include_domains · array · optionnel
    Only return results from these domains, e.g. ["docs.python.org"].

  Exemple d'appel

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

  Exemple de retour

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

• fetch≈ 98 tokens

  Fetch the full text of a search result by its id (a URL). Returns {id, title, text, url, metadata} as JSON.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    An id from `search` (the page URL).

  Exemple d'appel

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

  Exemple de retour

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

• search≈ 93 tokens

  Search the web. Returns {results: [{id, title, url}]} as JSON; pass an id to `fetch` for the page text.

  Paramètres, retour & exemple (1)

  Paramètres

  • query · string · requis
    Search query.

  Exemple d'appel

  {"name": "search", "arguments": {"query": "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://api.contextfetch.dev/mcp