Convert PDFs, Word and PowerPoint files, images and spreadsheets to Markdown via the MinerU parsing API.
Setup
This project documents no single launch command; follow its repository instructions.
MinerU MCP
OpenDataLabOfficialChina
Related
More- MMinerU MCPOpenDataLabOfficialChinaLets agents use MinerU to parse PDFs, Word, PPT and images into LLM-ready Markdown or JSON.Databases & Data82.3k Repository stars
- MMarkItDown MCPMicrosoftOfficialConverts local or remote files such as PDFs and Office documents to Markdown for LLMs, using MarkItDown.Databases & Data191.6k Repository stars
- TTextIn OCR MCPTextInOfficialChinaExtracts text from images, PDFs and Word files with TextIn OCR, recognizes IDs and invoices, and converts documents to Markdown.Databases & Data29 Repository stars
- TTalonic MCPTalonic.aiOfficialExtracts schema-validated structured fields from PDFs, scans, images and forms through Talonic, with searchable history of past extractions.Databases & Data5 Repository stars
- MMarkdownify MCPzcaceresConverts PDF, PPTX, HTML, images, audio, web pages, YouTube transcripts and more into Markdown.Databases & Data3k Repository stars
- PpdfmuxNameetPExtracts PDFs by routing each page to PyMuPDF, Docling, OCR or an LLM fallback, re-extracting low-confidence pages and auditing the output for dropped pages.Databases & Data84 Repository stars