Agents-MCP-Hackathon/yolo-v11-pose-lab

Overview

This Space allows you to upload an image then the Ultralytics Yolo v11 vision model and extract human pose data in the form of annotated images or JSON data. See the help at the bottom of the app to connect to this app by MCP or code.

Demo

Check out a demo of using this space as an MCP server here: https://www.youtube.com/watch?v=cHsdDf50shw

Further reading

• —Pose Detection Task
• —OpenCV Annotations