MCP-server-readability-python
1
The Mozilla Readability Parser MCP Server is a Python implementation designed to extract and convert webpage content into clean, Markdown format, optimizing it for large language model processing. It is based on the Readability algorithm, aiming to remove non-essential content like ads and navigation for consistent Markdown conversion.
Mozilla Readability Parser MCP Server
A Python implementation of the Model Context Protocol (MCP) server that extracts and transforms webpage content into clean, LLM-optimized Markdown.
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?
- Uses Readability algorithm to extract relevant content
- Eliminates noise like ads and popups
- Reduces token usage by removing unnecessary HTML/CSS
- Provides consistent Markdown for better LLM processing
- Handles complex web pages with dynamic content
Quick Start
- Start the server via
fastmcp run server.py
Dependencies
- readability-lxml
- html2text
- beautifulsoup4
- requests