mcp-mineru

TINKPA/mcp-mineru

3.3

If you are the rightful owner of mcp-mineru and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

MCP-MinerU is a Model Context Protocol server designed to enhance PDF parsing capabilities using the MinerU library.

Tools
2
Resources
0
Prompts
0

MCP-MinerU

PyPI version Python 3.10+ License

MCP server for document and image parsing via MinerU. Extract text, tables, and formulas from PDFs, screenshots, and scanned documents with MLX acceleration on Apple Silicon.

Installation

claude mcp add --transport stdio --scope user mineru -- \
  uvx --from mcp-mineru python -m mcp_mineru.server

This command installs and configures the server for all your Claude Code projects using uvx (no manual installation required).

Alternative methods: See for PyPI, source installation, and Claude Desktop configuration.

Features

  • Multiple format support: PDF, JPEG, PNG, and other image formats
  • OCR capabilities: Built-in text extraction from screenshots and photos
  • Table recognition: Preserves structure when extracting tables
  • Formula extraction: Converts mathematical equations to LaTeX
  • MLX acceleration: Optimized for Apple Silicon (M1/M2/M3/M4)
  • Multiple backends: Choose speed vs quality tradeoffs

Quick Start

Parse a PDF document

User: "Analyze the tables in research_paper.pdf"
Claude: [Calls parse_pdf tool] "The paper contains 3 tables..."

Extract text from a screenshot

User: "What does this screenshot say? image.png"
Claude: [Calls parse_pdf tool] "The screenshot contains..."

Check system capabilities

User: "Which backend should I use?"
Claude: [Calls list_backends tool] "Your system has Apple Silicon M4..."

For more examples, see .

Tools

parse_pdf

Parse PDF and image files to extract structured content as Markdown.

Parameters:

  • file_path (required): Absolute path to file (PDF, JPEG, PNG, etc.)
  • backend (optional): pipeline | vlm-mlx-engine | vlm-transformers
  • formula_enable (optional): Enable formula recognition (default: true)
  • table_enable (optional): Enable table recognition (default: true)
  • start_page (optional): Starting page for PDFs (default: 0)
  • end_page (optional): Ending page for PDFs (default: -1)

list_backends

Check system capabilities and get backend recommendations.

Returns: System information, available backends, and performance recommendations.

Supported Formats

  • PDF documents (.pdf)
  • JPEG images (.jpg, .jpeg)
  • PNG images (.png)
  • Other image formats (WebP, GIF, etc.)

Performance

Benchmarked on Apple Silicon M4 (16GB RAM):

  • pipeline: ~32s/page, CPU-only, good quality
  • vlm-mlx-engine: ~38s/page, Apple Silicon optimized, excellent quality
  • vlm-transformers: ~148s/page, highest quality, slowest

Documentation

  • - Detailed installation options
  • - How to update to the latest version
  • - More use cases and API reference
  • MinerU Documentation - Underlying parsing engine

Development

git clone https://github.com/TINKPA/mcp-mineru.git
cd mcp-mineru
uv pip install -e ".[dev]"

# Run tests
pytest

# Format code
black src/
ruff check src/

License

Apache License 2.0 - see file for details.

Acknowledgments

Built on top of MinerU by OpenDataLab.