MinerU

Wraps MinerU's document parsing API with six tools for extracting text, tables, and formulas from PDFs, Office docs, and images. You get mineru_parse for single URLs, mineru_upload_batch for local files, and mineru_batch for up to 200 documents at once. Status and download tools handle async workflows and save results as markdown with preserved filenames. Supports two models: pipeline for speed on simple docs, VLM for 90%+ accuracy on complex layouts. Includes OCR across 109 languages and page range selection. Requires a MinerU API key. Reach for this when you need production document extraction without running models locally, especially for batch processing scanned PDFs or converting documentation archives to markdown.