ContextFetch MCP Server

by contextfetch Your server? Claim it

answering

ContextFetch is answering right now. Last checked 14 min ago. 513 installs a week from npm. It exposes 14 tools. Last commit 26 Oct 2026.

Web search and any page as LLM-ready Markdown for AI agents. Free keyless tier, no signup.

Installs per day peak 330 · avg 35 · -5% w/w

a month agotoday

Uptime history 13 days of history · worst day 15%

13 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

37 ms

Response time

average over 24h

513

Installs / week

npm and PyPI

What changed 19

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 21 October 2026. No other catalogue keeps this.

29 Oct a tool description was rewritten contextfetch_agent

29 Oct a tool changed the parameters it asks for contextfetch_agent

28 Oct a tool appeared contextfetch_agent

28 Oct a tool description was rewritten contextfetch_agent

28 Oct a tool changed the parameters it asks for contextfetch_agent

26 Oct a tool changed the parameters it asks for contextfetch_auto_reload

25 Oct 8 tool descriptions were rewritten contextfetch_answer, contextfetch_auto_reload, contextfetch_balance and 5 more

25 Oct a tool changed the parameters it asks for contextfetch_auto_reload

22 Oct 2 tool descriptions were rewritten contextfetch_deep_research, contextfetch_research

21 Oct a tool description was rewritten contextfetch_deep_research

and 1 more, back to 21 October 2026

ContextFetch does not always answer

Over the last week it answered 99.1% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

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

Settings → Connectors → Add custom connector, then paste this address

https://api.contextfetch.dev/mcp

~/.codex/config.toml

[mcp_servers.mcp]
url = "https://api.contextfetch.dev/mcp"

.cursor/mcp.json

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

.vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://api.contextfetch.dev/mcp"
    }
  }
}

Available tools 14

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

contextfetch

contextfetch_agent

A 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; when the pages lack the answer it searches again with new queries. Use it when you want the answer itself; for quotes only use contextfetch_answer, for raw sources contextfetch_search. ~2 s. Costs $0.001 ($1 per 1,000); depth standard (a short research agent, ~10-15 s, for questions that need several facts) $0.002.

contextfetch_answer

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 $0.001 ($1 per 1,000).

contextfetch_auto_reload

Turn 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 cannot be raised above $500 here.

contextfetch_balance

Show 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_crawl

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 $0.001 per page returned ($1 per 1,000).

contextfetch_deep_research

Deep 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, key facts, a section per sub-topic and the sources, every passage quoted verbatim with [n]. Costs $0.003 a report ($3 per 1,000). For a quick evidence pack use contextfetch_research.

contextfetch_extract_url

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.

contextfetch_find_similar

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.

contextfetch_get_free_key

Get 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 <key>`.

contextfetch_map

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 $0.001 ($1 per 1,000).

contextfetch_research

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 $0.001 per sub-query that runs ($1 per 1,000). 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".

contextfetch_search

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.

fetch

fetch

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

search

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

Endpoints

URL	Transport	State	Latency	Checked
https://api.contextfetch.dev/mcp	streamable-http	answering	62 ms	14 min ago

Alternatives to ContextFetch

same job, measured the same way

Andi Search

by andiai

Real-time web search and page fetch for AI agents from Andi's own index. LLM-ready markdown output.

answering

Web Search

by hec-ovi

Keyless multi-engine web search, fetch, and clean-Markdown read for AI agents. No API keys.

92 installs/wk local only

Vibes-Coded Agent Tools

by doteyeso-ops

Web search, page-to-markdown, memory, leases and proof for agents. x402, no signup.

33 tools answering

SearchForge

by divyanshu-iitian

Free open-source web search and page reading for LLMs, AI agents, and RAG.

local only

searchio

by ioserviceslabs

Keyless web search and page reading for AI agents, built to get past bot walls.

58 installs/wk local only

Web Reader & Search (Tanod)

by tanod

Web search for agents: page to Markdown, screenshots, news search, metadata, sitemaps and RDAP.

40 tools answering

Dipper

by dipper-search

Web search and page fetch for AI agents. Results come from a shared cache; cached calls cost less.

2 tools answering

by neurobird

Web search for AI agents. Ranked results with page passages already extracted, plus URL to markdown.

2 tools answering

ContextFetch — questions

Answers built from our own checks of this server.

What can ContextFetch do?

It exposes 14 tools, read directly from the server on our last check. Among them: contextfetch_agent, contextfetch_answer, contextfetch_auto_reload, contextfetch_balance, contextfetch_crawl, contextfetch_deep_research and 8 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is ContextFetch working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 37 ms. The bar chart above shows every period we have measured.

How do I connect ContextFetch?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does ContextFetch need an API key?

No. ContextFetch completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 14 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is ContextFetch?

It answers our handshake in 37 ms on average, which is faster than 99% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.

How many people use ContextFetch?

The npm package @contextfetch/mcp was installed 513 times in the last week. Week over week that is -5%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is ContextFetch open source?

The code is open source: it is published under the MIT licence, written in TypeScript, 0 stars on GitHub and 1 open issue. The licence covers the code in the repository, not the hosted service at api.contextfetch.dev, which runs on its operator's own terms.