</>MCP Agents Market
MCP Server

MinerU

by opendatalab77.8kPythonUpdated 2026-08-16

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Claude DesktopCursorWindsurf

MinerU is an MCP server that converts complex document formats including PDFs, Office files (DOCX, PPTX, XLSX), and images into clean, structured markdown and JSON optimized for large language model workflows. Developed by opendatalab, it extracts text in natural reading order while preserving semantic structure, tables, formulas, and images. The server supports 109 languages via OCR, handles scanned documents and handwriting, and integrates natively with RAG frameworks, LangChain, Dify, and AI coding tools through MCP protocol.

Key Features

Parses PDF, DOCX, PPTX, XLSX, and image files into markdown or JSON with preserved layout structure
Converts mathematical formulas to LaTeX and tables to HTML with high accuracy
OCR engine supports 109 languages, scanned documents, handwriting, and multi-column layouts
Removes headers, footers, and page numbers automatically while maintaining semantic flow
Dual-engine architecture (VLM + OCR) with configurable parsing strength for speed vs. accuracy
Runs on CPU-only environments or accelerates with GPU/MPS; supports offline deployment
Native integrations with Cursor, Claude Desktop, Windsurf, LangChain, Dify, FastGPT, and RAGFlow
Multiple backends (pipeline, hybrid-engine, vlm-engine) balancing resource usage and parsing quality

Use Cases

  • 01Converting research papers and technical documentation into LLM-readable markdown for RAG pipelines
  • 02Extracting structured data from invoices, financial reports, and spreadsheets for agent workflows
  • 03Preprocessing scanned legal documents and handwritten notes for search and retrieval systems
  • 04Building document Q&A systems by parsing multi-format corporate knowledge bases
  • 05Preparing training datasets from academic papers with complex formulas and diagrams
  • 06Enabling AI coding assistants to reference technical manuals and API documentation

Related MCP Servers

View more

MinerU — FAQ

What is the MinerU MCP server?+

MinerU is an MCP server that transforms PDFs, Office documents, and images into structured markdown or JSON for agentic AI workflows. It preserves document layout, extracts tables and formulas, and supports 109 languages through OCR.

How do I install the MinerU MCP server?+

Install via pip with 'pip install -U mineru[all]' or from source by cloning the GitHub repository. Docker deployment is also available for Linux and Windows WSL2 environments. Python 3.10-3.13 is required.

Which AI clients work with MinerU?+

MinerU supports Cursor, Claude Desktop, and Windsurf through its MCP server interface. It also integrates with LangChain, LlamaIndex, Dify, FastGPT, RAGFlow, and other RAG frameworks via Python SDK and REST API.

Do I need an API key or GPU to use MinerU?+

No API keys are required. MinerU runs locally and offline. The pipeline backend works on CPU-only systems with 16GB RAM, while hybrid/vlm backends require 8GB+ VRAM for GPU acceleration and deliver higher accuracy.

Is MinerU free to use?+

Yes, MinerU is open source under a custom license based on Apache 2.0. It is free for both personal and commercial use with certain conditions outlined in the MinerU Open Source License.

What file formats does MinerU support?+

MinerU parses PDF, DOCX, PPTX, XLSX, and common image formats (JPG, PNG). It handles both native digital documents and scanned/OCR documents, including complex layouts, formulas, tables, and multilingual content.

How do I install MinerU?+

Open the source repository on GitHub and follow its README. MinerU is a mcp server — MCP Agents Market links you directly to the official repo.

Is MinerU free?+

MinerU is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches