Defuddle Fetch

domdomegg/defuddle-fetch-mcp-server

Fetches web content and converts it to clean markdown using Defuddle instead of the standard Readability library. Exposes a single fetch tool that takes a URL and optional parameters for pagination (start_index, max_length) and output format (raw HTML or markdown). Returns the main content stripped of navigation and clutter, plus metadata like title, author, publication date, and word count. Built as a drop-in replacement for the default MCP fetch server, with better extraction on modern sites especially GitHub. Install via npx and point Claude at it when you need cleaner web scraping than Readability provides.

GitHub stars: 6
tool: 1
transport: STDIO
last updated: Dec 5, 2025

View on GitHub

Tools

1 tools

Public tool metadata for what this MCP can expose to an agent.

fetchFetches a URL from the internet and extracts its contents as clean, markdown text using Defuddle

Fetches a URL from the internet and extracts its contents as clean, markdown text using Defuddle

No parameter schema in public metadata yet.

Readme

defuddle-fetch-mcp-server

A Model Context Protocol server that provides web content fetching capabilities using the Defuddle library. This server enables LLMs to retrieve and process content from web pages, automatically cleaning up the HTML and converting it to clean, readable markdown.

This is a drop-in replacement for the default fetch MCP server that uses Readability. This generally provides better results for most modern webpages.