MCP YOLOE: Zero-Shot Object Detection & Segmentation
Overview
MCP-YOLO
MCP-YOLO is a powerful Model Context Protocol server that grants AI agents advanced computer vision capabilities. Unlike traditional YOLO models that only detect a fixed list of objects, this server uses Zero-Shot Learning to detect and segment anything you describe.
Key Features
- Zero-Shot Detection: Detect arbitrary objects using natural language prompts.
- Precision Segmentation: Get exact polygon masks for every detected object.
- Flexible Inputs: Works with local file paths, remote image URLs, and Base64 strings.
- Agent-First: Designed specifically for integration with Claude, IDEs, and autonomous workspace agents.
Example Usage
Ask your agent to:
"Find the 'vintage typewriter' in this image and give me its exact coordinates."
Performance
Uses the state-of-the-art YOLOE26-L architecture, providing a perfect balance of high precision (55.0 mAP) and rapid inference (~6.2ms on T4 GPUs).
Server Config
{
"mcpServers": {
"mcp-yolo": {
"command": "uvx",
"args": [
"mcp-yolo"
]
}
}
}Project Info
Created At
4 months agoUpdated At
4 months agoAuthor Name
rjn32sStar
-Language
-License
-