MCP-PDF2MD logo

MCP-PDF2MD

by FutureUnreal

MCP-PDF2MD is a high-performance PDF to Markdown conversion service powered by MinerU API. It supports batch processing for local files and URL links with structured output.

View on GitHub

Last updated: N/A

What is MCP-PDF2MD?

MCP-PDF2MD is a service that converts PDF files to structured Markdown format, supporting both local files and URL links. It integrates with LLM clients like Claude Desktop and leverages the MinerU API for high-quality extraction.

How to use MCP-PDF2MD?

  1. Clone the repository. 2. Create a virtual environment and install dependencies using uv. 3. Configure environment variables in a .env file with your MinerU API key. 4. Start the service using uv run pdf2md. 5. Optionally, configure Claude Desktop to use the service.

Key features of MCP-PDF2MD

  • Format Conversion: PDF to Markdown

  • Multi-source Support: Local files and URLs

  • Intelligent Processing: Automatic method selection

  • Batch Processing: Efficient handling of large volumes

  • MCP Integration: Seamless with LLM clients

  • Structure Preservation: Maintains document structure

  • Smart Layout: Human-readable order for complex layouts

  • Formula Conversion: Recognizes and converts formulas to LaTeX

  • Table Extraction: Recognizes and converts tables

  • Cleanup Optimization: Removes headers, footers, etc.

  • High-Quality Extraction: Text, images, and layout

Use cases of MCP-PDF2MD

  • Converting research papers to Markdown for easier editing

  • Extracting content from PDF reports for analysis

  • Integrating PDF conversion into LLM workflows

  • Batch converting a large number of PDF documents to Markdown for archiving

FAQ from MCP-PDF2MD

What is the MinerU API?

The MinerU API is used for PDF content extraction, providing high-quality text, image, and layout information.

How do I get a MinerU API key?

Register on the MinerU website, apply for API testing qualification, and generate your API key on the API Management page.

Where should I configure the MinerU API key?

You can set it in the .env file or in the Claude Desktop configuration. The Claude Desktop configuration takes precedence.

What MCP tools are available?

The server provides convert_pdf_url for converting PDF URLs and convert_pdf_file for converting local PDF files.

What are the system requirements?

The system requires Python 3.10 or higher.