YOLO Computer Vision

Enables computer vision capabilities using YOLO models for object detection, segmentation, classification, and pose estimation on images and camera feeds

The YOLO MCP Server enables AI assistants to perform computer vision tasks using state-of-the-art YOLO (You Only Look Once) models. Built with Python using FastMCP and Ultralytics, it provides tools for object detection, segmentation, classification, and pose estimation on images, as well as real-time camera analysis. The implementation offers both direct model integration and CLI-based approaches, supports model training and validation, and includes comprehensive image analysis that combines multiple model results. This server bridges the gap between AI assistants and computer vision capabilities, making it valuable for applications requiring visual understanding of user-provided images or camera feeds.