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.
OCR-MCP is a complete AI OCR webapp and MCP server. It provides a web interface for drag-and-drop OCR, scanning, and batch processing, and a FastMCP server for agentic IDEs like Claude, Cursor, Windsurf. It supports 13 OCR engines, WIA scanner, preprocessing, and workflow pipelines.
Features
Compatibility
Quick start
Use cases
Alternatives
Related searches
Comments
- SSpencer BrownMay 12, 2026
Current OCR models handle handwriting and complex layouts better than older tools.
- Quinn KimMay 8, 2026
State-of-the-art OCR capabilities via FastMCP server — quality that matches commercial tools.
- SSpencer NguyenApr 25, 2026
Works with diverse document formats through a consistent MCP interface.
- OOaklyn JohnsonMar 5, 2026
Good for AI workflows that need to extract text from images or scanned documents.