imagesorcery-mcp

Author: sunriseapps

Description: 🪄 ImageSorcery MCP – an MCP server that equips AI assistants with local image-processing tools (crop, resize, detect objects, OCR, drawing, etc.) built on OpenCV, Ultralytics and EasyOCR.

Stars: 84
Forks: 7
License: MIT License
Category: Open Source

Overview

Transform Augment Code into a Computer Vision Powerhouse with ImageSorcery MCP

Give Augment Code the ability to see, process, and manipulate images directly in your development workflow – all running locally with zero API costs.

ImageSorcery MCP transforms Augment Code from a pure coding assistant into a comprehensive development tool that can handle image processing tasks alongside your code. Whether you're building a computer vision app, processing user uploads, or preparing training data, Augment can now crop images, detect objects, extract text with OCR, and perform dozens of other image operations – all while helping you write the code that uses them.

Seamless Integration with Your Development Workflow

Connect ImageSorcery to Augment Code and watch your productivity soar. Need to batch process images for your web app? Just tell Augment: "Resize all images in the assets folder to 300x300, add a watermark, and generate the CSS for responsive display." Augment will handle the image processing AND write the corresponding HTML/CSS code. Working on a machine learning project? Ask Augment to "Extract all faces from this training dataset, crop them to 224x224, and create the data loading script for PyTorch." The AI handles both the computer vision tasks and the Python code generation in one seamless workflow.

Powerful Local Processing, Zero Dependencies on External APIs

Unlike cloud-based image services, ImageSorcery runs entirely on your machine using OpenCV, Ultralytics YOLO models, and EasyOCR. This means Augment Code can process sensitive images without sending them anywhere, there are no API rate limits to worry about, and you can work offline. Perfect for developers building applications that handle user-generated content, medical imaging, or any scenario where data privacy matters. Plus, with pre-trained models for object detection and text recognition built-in, Augment can help you prototype computer vision features instantly without the usual setup headaches.

Ready to supercharge your development workflow? Add ImageSorcery MCP to your Augment Code setup and start building image-aware applications with the power of AI-assisted development and local computer vision processing working in perfect harmony.

Installation

  1. Prerequisites:

    • Python 3.9 or newer
    • Git

  2. Clone the repository
    git clone https://github.com/sunriseapps/imagesorcery-mcp.git
    cd imagesorcery-mcp

  3. Create and activate a virtual environment (recommended)
    python -m venv .venv
    source .venv/bin/activate # Windows: .venv\Scripts\activate

  4. Install dependencies
    pip install -r requirements.txt

  5. Optional – install in editable mode (if you plan to develop)
    pip install -e .

  6. Configuration
    • Copy .env.example to .env and set environment variables as needed, e.g.
    MCP_HOST=0.0.0.0
    MCP_PORT=8080
    MCP_AUTH_TOKEN=<your-token>

  7. Run the server
    python -m imagesorcery_mcp # or whatever entry-point the package provides

  8. Verify
    Open http://localhost:8080/health or http://localhost:8080/mcp/tools to make sure the service responds.

## Available Tools