mineru-mcp
MCP server for MinerU document parsing API — extract text, tables, and formulas from PDFs, DOCs, and images.
Features
- VLM model — 90%+ accuracy for complex documents
- Pipeline model — Fast processing for simple documents
- Local file upload — Upload files from disk for batch parsing
- Batch processing — Parse up to 200 documents at once
- Download & rename — Extract markdown with original filenames
- Page ranges — Extract specific pages only
- 109 language OCR support
- Optimized for Claude Code — 73% token reduction vs alternatives
Tools
| Tool | Description |
|---|---|
mineru_parse |
Parse a document URL |
mineru_status |
Check task progress, get download URL |
mineru_batch |
Parse multiple URLs (max 200) |
mineru_batch_status |
Get batch results with pagination |
mineru_upload_batch |
Upload local files for batch parsing |
mineru_download_results |
Download results as named markdown files |
Installation
Requires Node.js 18+ and a MinerU API key.
CLI Install (one-liner)
# Claude Code
claude mcp add mineru-mcp -e MINERU_API_KEY=your-api-key -- npx -y mineru-mcp
# Codex CLI (OpenAI)
codex mcp add mineru --env MINERU_API_KEY=your-api-key -- npx -y mineru-mcp
# Gemini CLI (Google)
gemini mcp add -e MINERU_API_KEY=your-api-key mineru npx -y mineru-mcp
