do-nothing.ai

Fetch MCP

open sourcestdio

Let agents fetch web pages and convert them to clean Markdown for processing

Updated 2026-02-15

Web & SearchFree· Open source, self-hosted.GitHubDocs

Official MCP server that gives agents the ability to fetch content from URLs and convert HTML pages to clean Markdown. Essential for agents that need to read documentation, extract content from URLs, or retrieve structured data from the web without a full browser.

Install

uvx mcp-server-fetch

Runtime: python

Tools (1)

fetch

Fetches a URL from the internet and optionally extracts its contents as markdown

urlmax_lengthstart_indexraw

Use Cases

  • ·Read documentation pages and convert to Markdown for agent ingestion
  • ·Extract content from URLs as part of research workflows
  • ·Fetch API responses and raw HTML for processing
  • ·Build agents that can reference live web content

Key Points

  • •Converts HTML to Markdown automatically for easier agent processing
  • •Supports raw fetch mode for non-HTML content
  • •Pagination via start_index for long pages
  • •Python-based, install with uvx or pip

Do-Nothing Score

Find out how close you are to Ghost CEO.

Take the quiz

Machine-Readable

This MCP is available as structured JSON via the API.

GET /api/v1/mcps/fetch