Reference Python MCP server that fetches a URL and converts the HTML to markdown. Supports chunked reading via start_index, raw output, and configurable robots.txt, user-agent and proxy behavior.
Connect
- 1Add the server to Codex
codex mcp add fetch -- uvx mcp-server-fetch
Configs are generated from the publisher's documented endpoint. Check their docs for plan requirements and scopes. New to this? Read the step-by-step tutorial.
Tools 1
fetchThings to ask
- “Fetch https://modelcontextprotocol.io and summarize it”
- “Read the changelog at this URL and list breaking changes”
- “Get the raw HTML of this page”