Markdown

概要

This Model Context Protocol (MCP) server leverages Playwright to intelligently extract the main content from any web page and convert it into clean, rich markdown. It excels at filtering out distracting elements like navigation, headers, footers, and advertisements, ensuring you get only the core information. Capable of handling dynamic and JavaScript-heavy sites, it preserves essential formatting, including headings, bold text, code blocks, lists, and tables, making it an invaluable tool for content collection and documentation across various AI clients.

主な機能

• Smartly identifies and extracts main content from web pages
• Generates clean markdown output by filtering non-content elements
• Preserves rich markdown formatting including headings, code blocks, lists, and tables
• Optionally includes image references and hyperlinks in the output
• Handles dynamic and JavaScript-heavy websites using Playwright
• 1 GitHub stars

ユースケース

• Extracting clean markdown content from documentation sites for AI models and research.
• Converting web articles, blogs, or technical content into structured markdown for easy consumption.
• Archiving website content by saving extracted markdown to local files for offline access or content management.