Skillget

ocr-mcp

mcp
Security Audit
Fail
Health Pass
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 14 GitHub stars
Code Fail
  • rm -rf — Recursive force deletion command in frontend/package.json
  • network request — Outbound network request in frontend/package.json
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

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.

README.md

OCR-MCP

FastMCP Version Ruff Linted with Biome Built with Just

Complete AI OCR webapp and MCP server. A web app for people (draganddrop OCR, scanner, batch) and a FastMCP 3.1 MCP server for agentic IDEsClaude, Cursor, Windsurfso agents can run OCR, preprocessing, and workflows as tools. Same 10+ engines, WIA scanner (Windows), and pipelines; one repo.

Topics: ocr, mcp, fastmcp, document-processing, scanner, wia, pdf, computer-vision, model-context-protocol, llm

Version
Python
FastMCP
License
OCR Engines
Scanner
Web UI
Status

What it does

  • Web app React (web_sota/) + FastAPI (backend/app.py): upload or scan, pick engine, get text/PDF/JSON. Ports 10858 (Vite) and 10859 (API). In-app Help (/help) documents the web UI, the MCP server, and OCR backends.
  • MCP server FastMCP 3.1 stdio: tools for OCR, preprocessing, scanner, workflows. Sampling defaults to local Ollama (http://127.0.0.1:11434/v1, model llama3.2) no cloud API key. Set OCR_SAMPLING_USE_CLIENT_LLM=1 to use the host IDEs LLM instead. Mistral OCR uses MISTRAL_API_KEY when you call that backend. See AI_FEATURES.md.

Features: 10+ backends (PaddleOCR-VL-1.5, DeepSeek-OCR-2, Mistral OCR, ) Auto backend selection Preprocessing (deskew, enhance, crop) Layout & table extraction Quality assessment WIA scanner Batch & pipelines Multi-format export

Docs

Doc Description
Install Install, run MCP, Web UI (start.ps1, ports 10858/10859), PyYAML notes, client config
Backend deps Web FastAPI backend: same venv as ocr-mcp, pyproject.toml, PyTorch, OCR_AUTO_INSTALL_DEPS
Technical Architecture, tools, config, development, packaging
OCR models Engines, capabilities, hardware (see also AI_MODELS.md)
Backend requirements Per-model pip packages, system deps, env/config
MCP toolset matrix Portmanteau tools, operation status, corpus v0
AI features Sampling, SEP-1577, agentic workflows, prompts
In-app Help Source for /help: webapp vs MCP vs backends (mirrors INSTALL / TECHNICAL)
SOTA Compliance Verified SOTA v12.0 Architecture

Also: JUSTFILE.md (just recipes) OCR-MCP_MASTER_PLAN.md (roadmap) tests/README.md (testing)

Install

Repository: github.com/sandraschi/ocr-mcp. Clone first uv sync needs a project on disk:

git clone https://github.com/sandraschi/ocr-mcp.git
Set-Location ocr-mcp
uv sync

Quick start

uv sync
just run

Web UI (recommended): from repo root run web_sota\start.ps1 (PowerShell). It clears ports 10858/10859, runs uv sync, restores PyYAML if needed (see docs/INSTALL.md), starts the FastAPI backend in a new window, starts Vite in another window, then opens http://localhost:10858 in your browser.

Or: just webapp if your justfile wraps the same flow.

If the start script fails, use two terminals from the ocr-mcp repo root:

  • Terminal 1 (backend):
    $env:PYTHONPATH = (Get-Location).Path; uv run uvicorn backend.app:app --host 127.0.0.1 --port 10859
  • Terminal 2 (frontend):
    cd web_sota; npm run dev -- --port 10858 --host

Then open http://localhost:10858

Tests: uv sync --extra dev then uv run python -m pytest or python scripts/run_tests.py --suite quick. See tests/README.md.

🛡️ Industrial Quality Stack

This project adheres to SOTA 14.1 industrial standards for high-fidelity agentic orchestration:

  • Python (Core): Ruff for linting and formatting. Zero-tolerance for print statements in core handlers (T201).
  • Webapp (UI): Biome for sub-millisecond linting. Strict noConsoleLog enforcement.
  • Protocol Compliance: Hardened stdout/stderr isolation to ensure crash-resistant JSON-RPC communication.
  • Automation: Justfile recipes for all fleet operations (just lint, just fix, just dev).
  • Security: Automated audits via bandit and safety.

License

MIT see LICENSE.

Reviews (0)

No results found