ContextFetch MCP

An official MCP server provided by ContextFetch that enables AI agents to perform web searches and retrieve page contents as clean Markdown. It supports tools for searching the web, mapping site structures, crawling pages, and managing API credits, offering a keyless tier for immediate use.

Endpoint and access

No sign-in: your client connects and lists tools immediately, with no account or key.

No sign-inEndpoint checked 2026-10-20Operated by ContextFetch

MCP endpoint (Streamable HTTP)

https://api.contextfetch.dev/mcp

Vendor documentation

What you can do with it

Perform web searches with Exa-compatible queries
Convert any URL into clean Markdown for LLM context
Crawl and map website structures for RAG pipelines
Manage API credits and auto-reload settings

Tools advertised by the last live check:

contextfetch_search
contextfetch_extract_url
contextfetch_find_similar
contextfetch_research
contextfetch_deep_research
contextfetch_answer
contextfetch_crawl
contextfetch_map
contextfetch_balance
contextfetch_auto_reload
contextfetch_get_free_key
search
fetch

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

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

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add contextfetch-mcp --url https://api.contextfetch.dev/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable contextfetch-mcp in your MCP settings.

Cursor configuration

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

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.

Cline configuration

{
  "mcpServers": {
    "contextfetch-mcp": {
      "type": "streamableHttp",
      "url": "https://api.contextfetch.dev/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start contextfetch-mcp and inspect its tools.

VS Code configuration

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

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

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

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

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

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

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

Ground your agent in cited data

ContextFetch MCP gives your agent tools. Koskamo gives it reviewed, cited facts to check its answers against. Add it as a second MCP server; public reads need no API key.

Connect Koskamo Browse datasets

See all 1,282

Do you run ContextFetch MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing