MinerU PDF Parser
Convert complex documents (PDF, Word, PPT, Excel, Images) into high-quality, clean Markdown. It handles LaTeX formulas, tables, and images while providing built-in OCR for scanned documents.
Key Features:
- Zero-Config Start: Use the lightweight Agent API for files ≤ 10 MB / 20 pages without any token.
- Power Mode: Full token support for large files (up to 200 MB / 200 pages), batch processing, and advanced exports (DOCX, HTML, LaTeX).
- Flexible Output: Pipe results directly to stdout, JSON, or integrated sinks like Obsidian, Notion, and Slack.
- MCP Server: Ready to be exposed as an MCP server for AI agents.
Use when:
- Converting documents to Markdown for LLM consumption.
- Extracting structured data from PDFs.
- Running OCR on scanned documents.
- Batch-processing a folder of research papers into a knowledge base.
Not yet audited
This skill has not been reviewed by our automated audit pipeline yet.