Provides document parsing capabilities for JPEG images (along with PNG, PDF, DOC, DOCX, PPT, PPTX formats) through the MinerU API, with support for OCR, formula recognition, table recognition, and page range selection across 109 languages.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MinerU MCP Serverparse this PDF from pages 1-5 using VLM model with OCR enabled"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mineru-mcp
MCP server for MinerU document parsing API - optimized for Claude Code.
Features
4 optimized tools with concise descriptions (~73% token reduction vs alternatives)
VLM model support (90%+ accuracy) and pipeline mode (faster)
Page range selection - parse specific pages only
Batch processing - up to 200 documents at once
Pagination - efficient handling of large batch results
109 language OCR support
Installation
Claude Code
Claude Desktop
Add to your Claude Desktop config:
Configuration
Environment Variable | Default | Description |
| (required) | Your MinerU API Bearer token |
|
| API base URL |
|
| Default model: |
Get your API key at mineru.net
Tools
mineru_parse
Parse a single document URL.
mineru_status
Check task progress and get download URL.
Concise output: done | abc-123 | https://cdn-mineru.../result.zip
mineru_batch
Parse multiple documents in one batch (max 200).
mineru_batch_status
Get batch results with pagination.
Supported Formats
PDF, DOC, DOCX, PPT, PPTX
PNG, JPG, JPEG
Limits
Single file: 200MB max, 600 pages max
Daily quota: 2000 pages at high priority
Batch: max 200 URLs per request
License
MIT
Links
MinerU - Document parsing service
MinerU GitHub - Open source version
MCP Specification - Model Context Protocol