Doc Scraper MCP Server

A Model Context Protocol (MCP) server that provides documentation scraping functionality. This server converts web-based documentation into markdown format using jina.ai's conversion service.

Features

• Scrapes documentation from any web URL
• Converts HTML documentation to markdown format
• Saves the converted documentation to a specified output path
• Integrates with the Model Context Protocol (MCP)

Installation

Installing via Smithery

To install Doc Scraper for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @askjohngeorge/mcp-doc-scraper --client claude

1. Clone the repository:

git clone https://github.com/askjohngeorge/mcp-doc-scraper.git
cd mcp-doc-scraper

2. Create and activate a virtual environment:

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

3. Install the dependencies:

pip install -e .

Usage

The server can be run using Python:

python -m mcp_doc_scraper

Tool Description

The server provides a single tool:

• Name: scrape_docs
• Description: Scrape documentation from a URL and save as markdown
• Input Parameters:
  • url: The URL of the documentation to scrape
  • output_path: The path where the markdown file should be saved

Project Structure

doc_scraper/
├── __init__.py
├── __main__.py
└── server.py

Dependencies

• aiohttp
• mcp
• pydantic

Development

To set up the development environment:

1. Install development dependencies:

pip install -r requirements.txt

2. The server uses the Model Context Protocol. Make sure to familiarize yourself with MCP documentation.

License

MIT License