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.

30
/ 100
Emerging

This tool helps you quickly extract text, tables, and document layouts from various files like PDFs, comics, or scanned images. You can drag-and-drop your documents into a web application, use a connected scanner, or integrate it with AI agents. It processes your input and provides the extracted information in text, PDF, or JSON formats. This is ideal for anyone who regularly needs to convert documents into structured, searchable data.

Use this if you need to extract information from documents, scans, or images using state-of-the-art OCR models, with options for a user-friendly web interface or integration with AI agents.

Not ideal if you require only basic text extraction from simple documents and do not need advanced layout analysis, table extraction, or integration with AI tools.

document-capture data-extraction content-digitization information-retrieval document-management
No Package No Dependents
Maintenance 13 / 25
Adoption 4 / 25
Maturity 13 / 25
Community 0 / 25

How are scores calculated?

Stars

7

Forks

Language

Python

License

MIT

Last pushed

Mar 16, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/sandraschi/ocr-mcp"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.