MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
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
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 morepublic-apis
A collective list of free APIs
awesome-python
The definitive list that answers "I want to do X in Python, which tool should I use?"
awesome-selfhosted
A list of Free Software network services and web applications which can be hosted on your own servers
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
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.