Empowers AI assistants with image processing capabilities such as cropping, resizing, object detection, and OCR through an MCP server.
ImageSorcery equips AI assistants with computer vision-based image recognition and editing tools by providing an MCP server that offers capabilities to modify and analyze images. It allows for cropping, resizing, rotating, and drawing on images, detecting objects using advanced models, extracting text with OCR, and retrieving detailed image metadata. With ImageSorcery, AI assistants can go beyond verbal descriptions and engage in visual manipulation, making them more versatile and effective in image-related tasks.
主な機能
01Draw text and shapes on images
02Crop, resize, and rotate images
03Get detailed image metadata
049 GitHub stars
05Detect objects using pre-trained models
06Extract text from images using OCR
ユースケース
01Numerating form fields on an image and creating a list of described fields
02Copying photos with specific objects from one folder to another
03Finding and cropping an image to center a specific object
