imagesorcery-mcp

Overview

ImageSorcery MCP is a comprehensive image processing server that enables AI assistants to perform various computer vision tasks locally. The server offers tools for image manipulation like cropping, resizing, rotating, drawing text and shapes, as well as advanced features like object detection, OCR, and background removal. By processing images locally, it ensures privacy while providing sophisticated image analysis capabilities. The project is well-maintained with regular updates and clear documentation.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• blur

  Blurs specified rectangular or polygonal areas of an image using OpenCV.

  Try:Blur the area from (150, 100) to (250, 200) with a blur strength of 21 in my image 'test_image.png'Try:Invert the area to blur the background instead of the main object
• change_color

  Changes the color palette of an image

  Try:Convert my image 'test_image.png' to sepiaTry:Apply a vintage color filter to my photo
• config

  View and update ImageSorcery MCP configuration settings

  Try:Show me the current configurationTry:Set the default detection confidence to 0.8
• crop

  Crops an image using OpenCV's NumPy slicing approach

  Try:Crop my image 'input.png' from coordinates (10,10) to (200,200)Try:Crop the center 400x400 pixels from my photo
• detect

  Detects objects in an image using models from Ultralytics

  Try:Detect objects in my image 'photo.jpg' with a confidence threshold of 0.4Try:Find all cars and pedestrians in this image with high confidence
• draw_arrows

  Draws arrows on an image using OpenCV

  Try:Draw a red arrow from (50,50) to (150,100) on my image 'photo.jpg'Try:Add an arrow pointing to the main object in the image
• draw_circles

  Draws circles on an image using OpenCV

  Try:Draw a red circle with center (100,100) and radius 50 on my image 'photo.jpg'Try:Circle all detected faces in the image
• draw_lines

  Draws lines on an image using OpenCV

  Try:Draw a red line from (50,50) to (150,100) on my image 'photo.jpg'Try:Connect related objects with lines in the diagram
• draw_rectangles

  Draws rectangles on an image using OpenCV

  Try:Draw a red rectangle from (50,50) to (150,100) on my image 'photo.jpg'Try:Highlight the main area of interest in the photo
• draw_texts

  Draws text on an image using OpenCV

  Try:Add text 'Hello World' at position (50,50) on my image 'photo.jpg'Try:Put a watermark in the bottom right corner of my photo
• fill

  Fills specified areas of an image with a color and opacity, or makes them transparent

  Try:Fill the area from (150, 100) to (250, 200) with semi-transparent red in my imageTry:Remove the background by making it transparent
• find

  Finds objects in an image based on a text description

  Try:Find all dogs in my image 'photo.jpg' with a confidence threshold of 0.4Try:Locate cars and trucks in this street scene

Comparable tools

Installation

FAQ

Does ImageSorcery MCP send images to external servers?

No, all image processing is done locally on your machine. No images are sent to any external servers.

What models does ImageSorcery MCP use for object detection?

It uses YOLO models (yoloe-11l-seg-pf.pt, yoloe-11s-seg-pf.pt, etc.) and supports custom models. You can see all available models with the 'models://list' resource.

Compare imagesorcery-mcp with