Mozilla Readability Parser MCP Server

🚀 Mozilla Readability Parser MCP Server

A Python-based implementation of the Model Context Protocol (MCP) server that extracts web page content and converts it into clean Markdown format suitable for LLM processing.

🚀 Quick Start

Start the server

fastmcp run server.py

Example request

curl -X POST http://localhost:8000/tools/extract_content \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com/article"}'

✨ Features

• Remove ads, navigation bars, footers, and other non-essential content.
• Convert clean HTML to well-formatted Markdown.
• Handle errors smoothly.
• Optimize the LLM processing flow.
• Lightweight and fast.

🤔 Why Not Just Fetch?

Compared to simple fetch requests, this server:

• Uses readability algorithms to extract relevant content.
• Eliminates noise such as ads, pop-ups, and navigation menus.
• Reduces token usage by removing unnecessary HTML/CSS.
• Provides a consistent Markdown format to improve LLM processing.
• Handles complex web pages with dynamic content.

📦 Installation

1. Clone the repository:

git clone https://github.com/jmh108/MCP-server-readability-python.git
cd MCP-server-readability-python

2. Create and activate a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows, use: venv\Scripts\activate

3. Install dependencies:

pip install -r requirements.txt

📚 Documentation

Tool Reference

extract_content

Fetch and convert web page content to clean Markdown.

Parameters:

{
  "url": {
    "type": "string",
    "description": "The URL of the website to parse",
    "required": true
  }
}

Return value:

{
  "content": "Markdown content..."
}

MCP Server Configuration

To configure the server in the MCP settings file, add the following:

{
  "mcpServers": {
    "readability": {
      "command": "fastmcp",
      "args": ["run", "server.py"],
      "env": {}
    }
  }
}

Then you can start and access the server through the parse tool.

🔧 Technical Details

Dependencies

• readability-lxml - Content extraction
• html2text - HTML to Markdown conversion
• beautifulsoup4 - Web page parsing
• lxml - XML processing

📄 License

This project is licensed under the MIT license. For more details, please refer to the LICENSE file.