jmh108_MCP-server-readability-python
1
The MCP Server Readability Parser is a Python implementation of an MCP server that extracts and optimizes webpage content into Markdown, using the Readability algorithm to eliminate unnecessary elements like ads and navigation. It is designed for efficient LLM processing and delivers consistent, cleanly formatted output.
MCP Server Readability Parser (Python / FastMCP)
Features
- Removes ads, navigation, footers and other non-essential content
- Converts clean HTML into well-formatted Markdown
- Handles errors gracefully
- Optimized for LLM processing
- Lightweight and fast
Why Not Just Fetch?
- Extracts only relevant content using Readability algorithm
- Eliminates noise like ads, popups, and navigation menus
- Reduces token usage by removing unnecessary HTML/CSS
- Provides consistent Markdown formatting for better LLM processing
- Handles complex web pages with dynamic content