ContextFetch

Connect it to your AI

Claude Code

claude mcp add --transport http contextfetch https://api.contextfetch.dev/mcp

Claude, ChatGPT, Cursor and other apps

Add it as a custom connector with this URL (Streamable HTTP):

https://api.contextfetch.dev/mcp

This server expects extra headers, usually an API key from its maker.

claude mcp add contextfetch -- npx -y @contextfetch/mcp@1.1.0

Cursor, VS Code and other apps (mcp.json)

{
  "mcpServers": {
    "contextfetch": {
      "url": "https://api.contextfetch.dev/mcp"
    }
  }
}

Tools it offers

14 tools, as the server itself reported during our check on Oct 31, 2026.

• contextfetch_searchSearch 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, d
• contextfetch_extract_urlFetch 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.
• contextfetch_find_similarFind 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.
• contextfetch_researchResearch 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 pac
• contextfetch_deep_researchDeep research in one call, no LLM: a deep search of the question, its sub-topics (or your sub_queries) as searches of their own, and the pages its list and index results link to, returned as one cited report: summary, ke
• contextfetch_answerAnswer 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 fo
• contextfetch_agentA finished answer to a question, written with [n] citations to live web sources: one deep search reads the top pages and an LLM (gpt-oss-120b) writes the answer from them only, saying what is missing rather than guessing
• contextfetch_crawlCrawl 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
• contextfetch_mapList 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 contextfetc
• contextfetch_balanceShow the API key's balance in dollars, daily burn rate (7-day average) and auto top-up settings, including the last auto-reload error if a payment failed. Needs an API key (Authorization: Bearer); free.
• contextfetch_auto_reloadTurn auto top-up on or off, or change it: when the balance drops below `threshold_usd`, the saved card adds `amount_usd`, up to `monthly_max_usd` per month. Needs an API key and a card saved at checkout. The monthly cap
• contextfetch_get_free_keyGet a free ContextFetch API key (no signup, no payment) with a $2.50 starter balance, for when the keyless daily limit runs out. One key per network, ever: keep the key it returns and use it as `Authorization: Bearer <ke
• searchSearch the web. Returns {results: [{id, title, url}]} as JSON; pass an id to `fetch` for the page text.
• fetchFetch the full text of a search result by its id (a URL). Returns {id, title, text, url, metadata} as JSON.

Questions