A computer vision-based MCP server that provides local image recognition and editing capabilities, including object detection, OCR, background removal, and various image processing tools.

Installation

pipx (Recommended)

pipx install imagesorcery-mcp
imagesorcery-mcp --post-install

Manual Virtual Environment Setup

python -m venv imagesorcery-mcp
source imagesorcery-mcp/bin/activate
pip install imagesorcery-mcp
imagesorcery-mcp --post-install

Configuration

Installation via pipx

"mcpServers": {
    "imagesorcery-mcp": {
      "command": "imagesorcery-mcp",
      "transportType": "stdio",
      "autoApprove": ["blur", "change_color", "config", "crop", "detect", "draw_arrows", "draw_circles", "draw_lines", "draw_rectangles", "draw_texts", "fill", "find", "get_metainfo", "ocr", "overlay", "resize", "rotate"],
      "timeout": 100
    }
}

Manual venv Installation

"mcpServers": {
    "imagesorcery-mcp": {
      "command": "/full/path/to/venv/bin/imagesorcery-mcp",
      "transportType": "stdio",
      "autoApprove": ["blur", "change_color", "config", "crop", "detect", "draw_arrows", "draw_circles", "draw_lines", "draw_rectangles", "draw_texts", "fill", "find", "get_metainfo", "ocr", "overlay", "resize", "rotate"],
      "timeout": 100
    }
}

HTTP Mode

"mcpServers": {
    "imagesorcery-mcp": {
      "url": "http://127.0.0.1:8000/mcp",
      "transportType": "http",
      "autoApprove": ["blur", "change_color", "config", "crop", "detect", "draw_arrows", "draw_circles", "draw_lines", "draw_rectangles", "draw_texts", "fill", "find", "get_metainfo", "ocr", "overlay", "resize", "rotate"],
      "timeout": 100
    }
}

Available Tools

Tool	Description
blur	Blurs specified rectangular or polygonal areas of an image using OpenCV
change_color	Changes the color palette of an image
config	View and update ImageSorcery MCP configuration settings
crop	Crops an image using NumPy-style slicing with OpenCV
detect	Detects objects in an image using models from Ultralytics
draw_arrows	Draws arrows on an image using OpenCV
draw_circles	Draws circles on an image using OpenCV
draw_lines	Draws lines on an image using OpenCV
draw_rectangles	Draws rectangles on an image using OpenCV
draw_texts	Draws text on an image using OpenCV
fill	Fills specified image areas with color or makes them transparent
find	Finds objects in an image by text description
get_metainfo	Gets metadata from an image file
ocr	Performs optical character recognition (OCR) on an image using EasyOCR
overlay	Overlays one image on top of another with transparency handling

Features

• Crop, resize, and rotate images with high precision
• Background removal
• Draw text and shapes on images
• Add logos and watermarks
• Object detection using modern models
• Extract text from images using OCR
• Access a wide range of pre-trained models for object detection
• Local image processing without sending to external servers

Usage Examples

copy photos with pets from folder `photos` to folder `pets`

Find a cat at the photo.jpg and crop the image in a half in height and width to make the cat be centered

Enumerate form fields on this `form.jpg` with `foduucom/web-form-ui-field-detection` model and fill the `form.md` with a list of described fields

Blur the area from (150, 100) to (250, 200) with a blur strength of 21 in my image 'test_image.png' and save it as 'output.png'

Convert my image 'test_image.png' to sepia and save it as 'output.png'

Notes

Requires Python 3.10+, ffmpeg, libsm6, libxext6, and libgl1-mesa-glx system libraries. The post-install script downloads the required models and installs the CLIP package. Works with Claude, Cursor, and Cline. All processing is performed locally without sending images to external servers.