futureunreal_mcp_pdf2md
by FutureUnrealPDF to Markdown Conversion with MCP Integration
Overview
The MCP-PDF2MD service is a high-performance tool designed to convert PDF files into structured Markdown format. It leverages the MinerU API and supports batch processing for both local files and URL links. This service is particularly useful for users who need to maintain document structure while converting PDFs to Markdown.
Key Features
- Format Conversion: Convert PDF files to structured Markdown format.
- Multi-source Support: Process both local PDF files and URL links.
- Batch Processing: Efficiently handle large volumes of PDF files.
- MCP Integration: Seamless integration with LLM clients like Claude Desktop.
- Structure Preservation: Maintain original document structure, including headings, paragraphs, lists, etc.
- Formula Conversion: Automatically recognize and convert formulas to LaTeX format.
- Table Extraction: Recognize and convert tables to structured format.
- Cleanup Optimization: Remove headers, footers, footnotes, and page numbers for semantic coherence.
System Requirements
- Software: Python 3.10+
Quick Start
- Clone the repository and enter the directory:
shell git clone https://github.com/FutureUnreal/mcp-pdf2md.git cd mcp-pdf2md - Create a virtual environment and install dependencies:
- Linux/macOS:
shell uv venv source .venv/bin/activate uv pip install -e . - Windows:
shell uv venv .venv\Scripts\activate uv pip install -e . - Configure environment variables:
Create a.envfile in the project root directory and set the following variables:
MINERU_API_BASE=https://mineru.net/api/v4/extract/task MINERU_BATCH_API=https://mineru.net/api/v4/extract/task/batch MINERU_BATCH_RESULTS_API=https://mineru.net/api/v4/extract-results/batch MINERU_API_KEY=your_api_key_here - Start the service:
shell uv run pdf2md
Claude Desktop Configuration
Add the following configuration in Claude Desktop:
-
Windows:
json { "mcpServers": { "pdf2md": { "command": "uv", "args": [ "--directory", "C:\\path\\to\\mcp-pdf2md", "run", "pdf2md", "--output-dir", "C:\\path\\to\\output" ], "env": { "MINERU_API_KEY": "your_api_key_here" } } } } -
Linux/macOS:
json { "mcpServers": { "pdf2md": { "command": "uv", "args": [ "--directory", "/path/to/mcp-pdf2md", "run", "pdf2md", "--output-dir", "/path/to/output" ], "env": { "MINERU_API_KEY": "your_api_key_here" } } } }
MCP Tools
The server provides the following MCP tools:
- convert_pdf_url: Convert PDF URL to Markdown
- convert_pdf_file: Convert local PDF file to Markdown
Getting MinerU API Key
- Visit MinerU official website and register for an account.
- Apply for API testing qualification here.
- Once approved, access the API Management page to generate your API key.
Demo
Input PDF
Output Markdown
License
MIT License - see the LICENSE file for details.
Credits
This project is based on the API from MinerU.
Invite Gmail Contacts
