Extracts text from PDFs page by page, runs OCR on scanned pages and pulls out page images, with a built-in web debugger.
Setup
This project documents no single launch command; follow its repository instructions.
MCP PDF Reader
deepseekmine
Related
More- PPDF MCPjztanLets agents search and read large PDFs or folders with hybrid search, selective page reads, tables and OCR.System & Files155 Repository stars
- PPDF Extraction MCP ServerxraywuExtracts text from local PDF files, with OCR support and optional page selection.System & Files33 Repository stars
- GGo Docs MCPDrolosoftReads, searches and extracts text from PDF, TXT, Markdown, DOCX, CSV and image files with OCR, caching and directory confinement.System & Files11 Repository stars
- HHushvert MCPhushvertOfficialConverts office documents, PDFs, images, audio, video and archives between formats, including LLM-ready Markdown, via the Hushvert hosted API.System & Files1 Repository stars
- KkordocchrisryugjConverts Korean HWP/HWPX, PDF and Office documents to Markdown and structured data, with form filling and document diff.System & Files2.7k Repository stars
- AanymdSylphxAIConverts PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images and audio/video into clean Markdown for AI agents.System & Files1k Repository stars