sandraschi/ocr-mcp
FastMCP server providing advanced OCR capabilities with current state-of-the-art models (DeepSeek-OCR, Florence-2, DOTS.OCR, PP-OCRv5, Qwen-Image-Layered decomposition), WIA scanner control, and multi-format document processing for PDFs, CBZ comics, and images.
Two ways to use it: a web app for humans (drag‑and‑drop OCR, scanner, batch) and a FastMCP 3.1 MCP server for agentic IDE clients—Claude, Cursor, Windsurf—so agents can run OCR, preprocessing, and workflows as tools. Both use the same 10+ OCR engines, WIA scanner (Windows), and pipelines; one repo.
GitHub topics (repo → About → Topics): ocr, mcp, fastmcp, document-processing, scanner, wia, pdf, computer-vision, model-context-protocol, llm
[](https://github.com/sandraschi/ocr-mcp/releases) [](https://python.org) [](https://github.com/jlowin/fastmcp) [](LICENSE) [](README#-ai-models--ocr-engines) [](README#-scanner-integration) [](README#-web-interface) [](OCR-MCP_MASTER_PLAN.md)
Loading reviews...