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)

Related MCP server: Markdownify MCP Server - UTF-8 Enhanced

Installation

Installing via Smithery

To install Doc Scraper for Claude Desktop automatically via Smithery:

1. Clone the repository:

2. Create and activate a virtual environment:

3. Install the dependencies:

Usage

The server can be run using Python:

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

Dependencies

• aiohttp

• mcp

• pydantic

Development

To set up the development environment:

1. Install development dependencies:

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

License

MIT License