YOLO MCP服务
强大的YOLO(You Only Look Once)计算机视觉服务,通过模型上下文协议(MCP)与Claude AI集成。该服务使Claude能够使用最先进的YOLO模型进行对象检测、分割、分类和实时相机分析。

特性
- 目标检测、分割、分类和姿态估计
- 实时摄像头集成用于活体检测
- 支持模型训练、验证和导出
- 结合多种模型的综合图像分析
- 支持文件路径和base64编码图像
- 与Claude AI无缝集成
安装说明
先决条件
- Python 3.10或更高版本
- Git(可选,用于克隆存储库)
环境设置
- 为项目创建一个目录并导航到该目录:
mkdir yolo-mcp-service
cd yolo-mcp-service- 从存储库下载项目文件或克隆:
# If you have the files, copy them to this directory
# If using git:
git clone https://github.com/GongRzhe/YOLO-MCP-Server.git .- 创建虚拟环境:
# On Windows
python -m venv .venv
# On macOS/Linux
python3 -m venv .venv- 激活虚拟环境:
# On Windows
.venv\Scripts\activate
# On macOS/Linux
source .venv/bin/activate- 运行安装脚本:
python setup.py安装脚本将:
- 检查你的Python版本 - 创建虚拟环境(如果尚未创建) - 安装所需的依赖项 - 生成MCP配置文件(MCP-config.json) - 输出包括Claude在内的不同MCP客户端的配置信息
- 注意安装脚本的输出,它看起来类似于:
MCP configuration has been written to: /path/to/mcp-config.json
MCP configuration for Cursor:
/path/to/.venv/bin/python /path/to/server.py
MCP configuration for Windsurf/Claude Desktop:
{
"mcpServers": {
"yolo-service": {
"command": "/path/to/.venv/bin/python",
"args": [
"/path/to/server.py"
],
"env": {
"PYTHONPATH": "/path/to"
}
}
}
}
To use with Claude Desktop, merge this configuration into: /path/to/claude_desktop_config.json下载YOLO型号
在使用该服务之前,您需要下载YOLO型号。该服务在以下目录中查找模型:
- 服务运行的当前目录
- A.
models子目录 - 在中配置的任何其他目录
CONFIG["model_dirs"]server.py中的变量
创建一个模型目录并下载一些常见模型:
# Create models directory
mkdir models
# Download YOLOv8n for basic object detection
curl -L https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt -o models/yolov8n.pt
# Download YOLOv8n-seg for segmentation
curl -L https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt -o models/yolov8n-seg.pt
# Download YOLOv8n-cls for classification
curl -L https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt -o models/yolov8n-cls.pt
# Download YOLOv8n-pose for pose estimation
curl -L https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt -o models/yolov8n-pose.pt对于Windows PowerShell用户:
# Create models directory
mkdir models
# Download models using Invoke-WebRequest
Invoke-WebRequest -Uri "https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt" -OutFile "models/yolov8n.pt"
Invoke-WebRequest -Uri "https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt" -OutFile "models/yolov8n-seg.pt"
Invoke-WebRequest -Uri "https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt" -OutFile "models/yolov8n-cls.pt"
Invoke-WebRequest -Uri "https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt" -OutFile "models/yolov8n-pose.pt"配置Claude
要与Claude一起使用此服务,请执行以下操作:
- 对于Claude web:在本地计算机上设置服务,并使用MCP客户端中设置脚本提供的配置。
- 对于Claude Desktop:
- 运行安装脚本并记录配置输出 - 找到您的Claude Desktop配置文件(路径在安装脚本输出中提供) - 将配置添加或合并到您的Claude Desktop配置文件中 - 重新启动克劳德桌面
在Claude中使用YOLO工具
1.首先检查可用型号
始终先检查您的系统上有哪些型号可用:
I'd like to use the YOLO tools. Can you first check which models are available on my system?
2.检测图像中的对象
要分析计算机上的图像文件:
Can you analyze this image file for objects?
/path/to/your/image.jpg
0.3
您还可以指定其他模型:
Can you analyze this image using a different model?
/path/to/your/image.jpg
yolov8n.pt
0.4
3.运行综合图像分析
有关结合对象检测、分类等的更详细分析:
Can you perform a comprehensive analysis on this image?
/path/to/your/image.jpg
0.3
4.图像分割
为了识别对象边界和创建分割蒙版:
Can you perform image segmentation on this photo?
/path/to/your/image.jpg
true
yolov8n-seg.pt
5.图像分类
为了对整个图像内容进行分类:
What does this image show? Can you classify it?
/path/to/your/image.jpg
true
yolov8n-cls.pt
5
6.使用电脑的摄像头
使用计算机的摄像头开始实时对象检测:
Can you turn on my camera and detect objects in real-time?
yolov8n.pt
0.3
获取最新的摄像头检测结果:
What are you seeing through my camera right now?
完成后停止相机:
Please turn off the camera.
7.高级模型操作
训练自定义模型
I want to train a custom object detection model on my dataset.
/path/to/your/dataset
yolov8n.pt
50
验证模型
Can you validate the performance of my model on a test dataset?
/path/to/your/trained/model.pt
/path/to/validation/dataset
将模型导出为不同格式
I need to export my YOLO model to ONNX format.
/path/to/your/model.pt
onnx
8.测试连接
检查YOLO服务是否正常运行:
Is the YOLO service running correctly?
故障排除
摄像头问题
如果相机不工作,请尝试不同的相机ID:
1
未找到型号
如果找不到模型,请确保已将其下载到配置的目录之一:
性能问题
为了在资源有限的情况下获得更好的性能,请使用较小的型号(例如,yolov8n.pt而不是yolov8x.pt)
