Skip to content
MCP server

ContextFetch

Web search and page-to-Markdown for agents, with a free keyless tier

Install
Pricing
Freemium
Platforms
CLI, API
Runs
Locally or Remotely
Version
1.1.0
Listing updated
2 days ago

About ContextFetch

ContextFetch is a freemium MCP server for web search and scraping. It can run locally on your machine or as a hosted remote server.

ContextFetch is built around returning less text. Its search tool brings back each page cut down to the passages that answer the query, ranked by a cross-encoder, rather than whole pages. Page extraction, similar-page lookup, crawling and a site map tool use the same idea.

The research tool runs several sub-queries on the server, dedupes pages and returns a single Markdown evidence pack with numbered sources quoted verbatim; the answer tool is extractive and generates no text. A free key tool claims the network's free allowance, and balance and auto top-up tools manage credits.

Without a key you get 25 searches a day per network; otherwise it is pay as you go at 1 dollar per 1,000 calls, with an Exa- and Tavily-compatible API underneath. Failed connections and 429 or 5xx responses are retried with backoff.

Install

Run in a terminal

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

Add to Settings → Connectors → Add custom connector

https://api.contextfetch.dev/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://api.contextfetch.dev/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

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

Add to ~/.codeium/windsurf/mcp_config.json

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

Add to your client's MCP settings (most use this shape)

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

Configuration

  • CONTEXTFETCH_API_KEYContextFetch API key. Leave unset for the free keyless tier (25 requests per day per IP).
  • CONTEXTFETCH_API_BASEAPI base URL, only for a self-hosted engine.

Tools this server provides (11)

Taken from the project documentation; the running server may differ.

contextfetch_search
Web search returning query-relevant passages.
contextfetch_extract_url
A public page as Markdown, optionally pruned by a query.
contextfetch_find_similar
Pages similar to a URL.
contextfetch_research
Server-side multi-sub-query evidence pack.
contextfetch_deep_research
Earlier name of the research tool, kept for existing setups.
contextfetch_answer
Extractive answer from top pages with numbered sources.
contextfetch_crawl
Crawls a site and returns pages as Markdown.
contextfetch_map
Lists a site's URLs from sitemaps and links.
contextfetch_balance
Remaining credits and auto-reload settings.
contextfetch_get_free_key
Claims the network's free API key.
contextfetch_auto_reload
Turns auto-reload on or off or changes it.

What it does

Pruned search results
Returns only passages relevant to the query.
Page to Markdown
Extracts public pages with tables kept.
Server-side research
One call runs sub-queries and builds an evidence pack.
Crawl and site map
Walks a site respecting robots.txt or lists its URLs.
Free keyless tier
25 searches a day with no signup.
Credit tools
Balance, free key and auto-reload controls.

Good for

  • Research a technical question with cited passages
  • Convert a docs page to clean Markdown for a prompt
  • Find pages similar to a given URL
  • Crawl a documentation site and pull relevant sections

Pricing

Freemium

Free keyless tier; pay as you go at $1 per 1,000 calls, top-ups from $10

Prices change. Check contextfetch.dev before you buy.

ContextFetch FAQ

What does it cost?

1 dollar per 1,000 searches, extractions and similar calls; crawl is per page returned.

Is there a free tier?

Yes, 25 searches a day per network with no key, plus a free key of 2,500 searches.

Does it generate answers?

No. Answers are extractive, quoting passages verbatim.

What does it need?

Node.js 18 or newer for the stdio package.

Is ContextFetch free?

ContextFetch has a free plan, with paid plans for more usage or features.

How do I add ContextFetch to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://api.contextfetch.dev/mcp

What are the best alternatives to ContextFetch?

The closest alternatives to ContextFetch are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and AI-Powered directory.

Alternatives to ContextFetch

  1. MCP server for AI clients to scrape sites with HTTP and stealth browser sessions

    Runs locally
    • 17 tools
    • Open source
    • 104K GitHub stars
    • Web search and scraping
  2. MCP server that lets AI agents search, scrape and interact with web pages

    • 3 tools
    • Remote
    • Freemium
    • 7.8K GitHub stars
    • Web search and scraping
  3. SearXNG Search

    MCP server

    MCP server for web search and page reading through a SearXNG instance

    Runs locally
    • 3 tools
    • Open source
    • 1.4K GitHub stars
    • Web search and scraping
  4. NeuralVerge

    MCP server

    Structured, source-tagged business and people data from 300+ sources for agents

    • 200 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Web search and scraping
  5. Search AI tools, agents and MCP servers and get install configs from inside your AI assistant.

    • 4 tools
    • Remote
    • Free
    • Developer tools
  6. Hosted MCP server that returns any Shopify store's products, prices and stock

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • E-commerce