YOLO MCP
A computer vision service that allows Claude to perform object detection, segmentation, classification, and real-time camera analysis using state-of-the-art YOLO models.
What is YOLO MCP?
YOLO MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to computer vision service that allows claude to perform object detection, segmentation, classification, and real-time camera analysis using state-of-the-art yolo models.
A computer vision service that allows Claude to perform object detection, segmentation, classification, and real-time camera analysis using state-of-the-art YOLO models.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A computer vision service that allows Claude to perform obje
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx yolo-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use YOLO MCP
YOLO MCP Server is a Python computer vision service that integrates state-of-the-art YOLO (You Only Look Once) models with Claude through the Model Context Protocol, enabling object detection, instance segmentation, image classification, and pose estimation on both local files and base64-encoded images. It also supports real-time camera analysis and model training, validation, and export operations. Researchers, security engineers, and developers use it to add powerful on-device vision capabilities to their AI workflows without needing to write inference code.
Prerequisites
- Python 3.10 or higher
- Git (to clone the repository)
- Sufficient disk space for YOLO model weights (yolov8n.pt is ~6 MB; larger models are bigger)
- A camera device if using real-time detection features
- An MCP-compatible client such as Claude Desktop or Windsurf
Clone the repository
Clone the YOLO-MCP-Server repository and enter the project directory.
git clone https://github.com/GongRzhe/YOLO-MCP-Server.git
cd YOLO-MCP-ServerCreate and activate a virtual environment
Create an isolated Python environment to avoid dependency conflicts.
python3 -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activateRun the setup script
Execute setup.py to install dependencies and generate the mcp-config.json file with the correct absolute paths for your system.
python setup.pyDownload YOLO model weights
Create a models directory and download the YOLOv8 nano weights for detection, segmentation, classification, and pose estimation.
mkdir models
curl -L https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt -o models/yolov8n.pt
curl -L https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt -o models/yolov8n-seg.pt
curl -L https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt -o models/yolov8n-cls.ptConfigure Claude Desktop
Merge the generated mcp-config.json output into your Claude Desktop configuration file and restart Claude Desktop.
YOLO MCP Examples
Client configuration
Claude Desktop configuration for YOLO MCP Server using the virtual environment's Python binary.
{
"mcpServers": {
"yolo-service": {
"command": "/absolute/path/to/YOLO-MCP-Server/.venv/bin/python",
"args": ["/absolute/path/to/YOLO-MCP-Server/server.py"],
"env": {
"PYTHONPATH": "/absolute/path/to/YOLO-MCP-Server"
}
}
}
}Prompts to try
Example prompts for running YOLO computer vision analysis through Claude.
- "List all YOLO models available on my system."
- "Detect all objects in the image at /Users/me/photos/street.jpg with a confidence threshold of 0.4."
- "Run segmentation on /tmp/room.jpg and describe what you see."
- "Perform a comprehensive analysis of /Users/me/photo.jpg using all available models."
- "Start the camera and detect any people or vehicles in real time."Troubleshooting YOLO MCP
Setup script fails with missing ultralytics package
Activate the virtual environment first (`source .venv/bin/activate`) and then run `python setup.py` again. The script installs ultralytics and other dependencies into the active environment.
Model not found error when analyzing an image
Check that the model file exists in the models/ directory or the current working directory. Run the `list_available_models` tool first to see which weights the server can find.
Claude Desktop config uses wrong Python path
Use the absolute path to the .venv/bin/python binary as shown in the setup script output. Using the system Python will cause import errors because ultralytics is only installed in the venv.
Frequently Asked Questions about YOLO MCP
What is YOLO MCP?
YOLO MCP is a Model Context Protocol (MCP) server that computer vision service that allows claude to perform object detection, segmentation, classification, and real-time camera analysis using state-of-the-art yolo models. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install YOLO MCP?
Follow the installation instructions on the YOLO MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with YOLO MCP?
YOLO MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is YOLO MCP free to use?
Yes, YOLO MCP is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
YOLO MCP Alternatives — Similar Data Science & ML Servers
Looking for alternatives to YOLO MCP? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up YOLO MCP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use YOLO MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.