Allows development and contributions through GitHub, with the repository available at github.com/shuminghuang/pdf2md-mcp.
Converts PDF files to Markdown format, extracting content using AI sampling. Supports both local file paths and URLs with incremental conversion capabilities.
Supports testing through Pytest, enabling quality assurance for the PDF to Markdown conversion functionality.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@PDF2MD MCP Serverconvert this PDF from https://example.com/report.pdf to markdown"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
PDF2MD MCP Server
An MCP (Model Context Protocol) server that converts PDF files to Markdown format using AI sampling capabilities.
Features
Convert PDF files to Markdown using AI content extraction
Support for both local file paths and URLs
Incremental conversion - resume from where you left off
Configurable output directory
Built with FastMCP for high performance
Related MCP server: markdown2pdf-mcp
Installation
Usage
As an MCP Server
Start the server:
The server will expose MCP tools for PDF to Markdown conversion.
Available Tools
convert_pdf_to_markdown
Converts a PDF file to Markdown format using AI sampling.
Parameters:
file_path(string): Local file path or URL to the PDF fileoutput_dir(string, optional): Output directory for the markdown file. Defaults to the same directory as input file (for local files) or current working directory (for URLs)
Returns:
output_file: Path to the generated markdown filesummary: Summary of the conversion taskpages_processed: Number of pages processed
Requirements
Python 3.10+
An MCP-compatible client with AI sampling capabilities
Network access for URL-based PDF files
Development
Setup
Running Tests
Code Formatting
License
MIT License - see LICENSE file for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.