opendatalab/MinerU-Ecosystem

**The official ecosystem toolkit for MinerU Open API**
Empowering developers and AI agents with seamless document parsing capabilities — PDF · Word · PPT · Images · Web pages → Markdown / JSON · VLM+OCR dual engine · 109 languages · MCP Server · LangChain / RAGFlow / Dify / FastGPT native integration.
中文文档
---
📖 Overview
**MinerU-Ecosystem** provides a full suite of tools, SDKs, and integrations built on top of the MinerU Open API. Whether you're building production pipelines, integrating with LangChain for RAG, or enabling AI agents to parse documents on the fly — this repository has you covered.
MinerU is an open-source, high-accuracy document parsing engine that converts unstructured documents (PDFs, images, Office files, etc.) into machine-readable Markdown and JSON, purpose-built for LLM pre-training, RAG, and agentic workflows.
**Core capabilities:**
- Formulas → LaTeX · Tables → HTML, accurate complex layout reconstruction
- Supports scanned docs, handwriting, multi-column layouts, cross-page table merging
- Output follows human reading order with automatic header/footer removal
- VLM + OCR dual engine, 109-language OCR recognition
---
🏗️ Repository Structure
---
🔑 Supported APIs
All components support both API modes:
| Comparison | 🎯 Precision Extract API | ⚡ Quick Parse API (Agent-Oriented) |
| --------------- | ----------------------------------------------------------- | ----------------------------------- |
| Auth | ✅ Token required | ❌ Not required (IP rate-limited) |
| Model Versions | pipeline (default) / vlm (recommended) / MinerU-HTML | Fixed lightweight pipeline model |
| File Size Limit | ≤ 200 MB | ≤ 10 MB |
| Page Limit | ≤ 200 pages | ≤ 20 pages |
| Batch Support | ✅ Supported (≤ 200 files) | ❌ Single file only |
| Output Formats | Markdown, JSON, Zip; optional export to DOCX / HTML / LaTeX | Markdown only |
🧭 Choose Your Integration Path
Not sure where to start? Pick the path that matches your use case:
---
🚀 Quick Start
💻 CLI (cli/)
A fast command-line tool for parsing documents directly from your terminal.
Installation
**Flash Extract (no login)**
**Precision Extract (login required)**
**Web Crawl**
**Batch Processing**
---
🐍 Python SDK
Installation
**Flash Extract (no token)**
**Precision Extract (token required)**
---
🐹 Go SDK
Installation
**Flash Extract**
**Precision Extract**
**Precision Extract with options**
**Batch Processing**
**Web Crawling**
---
🟦 TypeScript / JavaScript SDK
Installation
**Flash Extract**
**Precision Extract**
**Precision Extract with options**
**Batch Processing**
**Web Crawling**
---
🤖 Use with Claude / Cursor (MCP Server)
MinerU provides an official MCP Server allowing Claude Desktop, Cursor, Windsurf, and any MCP-compatible AI client to parse documents as a native tool.
> No API key needed — Flash mode works out of the box, free, up to 20 pages / 10 MB per file.
**Configure: claude_desktop_config.json / .cursor/mcp.json**
**Streamable HTTP mode (web-based MCP clients)**
**Tools exposed via MCP:**
| Tool | Description |
|---|---|
| parse_documents | Convert PDF, DOCX, PPTX, images, HTML to Markdown |
| get_ocr_languages | List all 109 supported OCR languages |
| clean_logs | Delete old server log files (when ENABLE_LOG=true) |
**Environment Variables:**
| Variable | Description | Default |
|---|---|---|
| MINERU_API_TOKEN | MinerU cloud API token | — |