Defuddle Fetch

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.