{"id":50754546,"url":"https://github.com/GongRzhe/YOLO-MCP-Server","last_synced_at":"2026-06-28T07:00:26.789Z","repository":{"id":281782911,"uuid":"946407526","full_name":"GongRzhe/YOLO-MCP-Server","owner":"GongRzhe","description":null,"archived":true,"fork":false,"pushed_at":"2025-03-11T07:08:47.000Z","size":41,"stargazers_count":36,"open_issues_count":4,"forks_count":18,"subscribers_count":3,"default_branch":"main","last_synced_at":"2026-05-27T10:37:15.181Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/GongRzhe.png","metadata":{"files":{"readme":"Readme.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-03-11T05:01:41.000Z","updated_at":"2026-05-26T06:08:02.000Z","dependencies_parsed_at":"2025-03-11T06:29:18.080Z","dependency_job_id":null,"html_url":"https://github.com/GongRzhe/YOLO-MCP-Server","commit_stats":null,"previous_names":["gongrzhe/yolo-mcp-server"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/GongRzhe/YOLO-MCP-Server","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GongRzhe%2FYOLO-MCP-Server","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GongRzhe%2FYOLO-MCP-Server/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GongRzhe%2FYOLO-MCP-Server/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GongRzhe%2FYOLO-MCP-Server/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GongRzhe","download_url":"https://codeload.github.com/GongRzhe/YOLO-MCP-Server/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GongRzhe%2FYOLO-MCP-Server/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34880189,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-28T02:00:05.809Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-06-11T04:00:24.044Z","updated_at":"2026-06-28T07:00:26.783Z","avatar_url":"https://github.com/GongRzhe.png","language":"Python","funding_links":[],"categories":["MCP Servers for Creative Work"],"sub_categories":["Computer Vision"],"readme":"# YOLO MCP Service\n\nA powerful YOLO (You Only Look Once) computer vision service that integrates with Claude AI through Model Context Protocol (MCP). This service enables Claude to perform object detection, segmentation, classification, and real-time camera analysis using state-of-the-art YOLO models.\n\n![](https://badge.mcpx.dev?type=server 'MCP Server')\n\n\n## Features\n\n- Object detection, segmentation, classification, and pose estimation\n- Real-time camera integration for live object detection\n- Support for model training, validation, and export\n- Comprehensive image analysis combining multiple models\n- Support for both file paths and base64-encoded images\n- Seamless integration with Claude AI\n\n## Setup Instructions\n\n### Prerequisites\n\n- Python 3.10 or higher\n- Git (optional, for cloning the repository)\n\n### Environment Setup\n\n1. Create a directory for the project and navigate to it:\n   ```bash\n   mkdir yolo-mcp-service\n   cd yolo-mcp-service\n   ```\n\n2. Download the project files or clone from repository:\n   ```bash\n   # If you have the files, copy them to this directory\n   # If using git:\n   git clone https://github.com/GongRzhe/YOLO-MCP-Server.git .\n   ```\n\n3. Create a virtual environment:\n   ```bash\n   # On Windows\n   python -m venv .venv\n   \n   # On macOS/Linux\n   python3 -m venv .venv\n   ```\n\n4. Activate the virtual environment:\n   ```bash\n   # On Windows\n   .venv\\Scripts\\activate\n   \n   # On macOS/Linux\n   source .venv/bin/activate\n   ```\n\n5. Run the setup script:\n   ```bash\n   python setup.py\n   ```\n   \n   The setup script will:\n   - Check your Python version\n   - Create a virtual environment (if not already created)\n   - Install required dependencies\n   - Generate an MCP configuration file (mcp-config.json)\n   - Output configuration information for different MCP clients including Claude\n\n6. Note the output from the setup script, which will look similar to:\n   ```\n   MCP configuration has been written to: /path/to/mcp-config.json\n   \n   MCP configuration for Cursor:\n   \n   /path/to/.venv/bin/python /path/to/server.py\n   \n   MCP configuration for Windsurf/Claude Desktop:\n   {\n     \"mcpServers\": {\n       \"yolo-service\": {\n         \"command\": \"/path/to/.venv/bin/python\",\n         \"args\": [\n           \"/path/to/server.py\"\n         ],\n         \"env\": {\n           \"PYTHONPATH\": \"/path/to\"\n         }\n       }\n     }\n   }\n   \n   To use with Claude Desktop, merge this configuration into: /path/to/claude_desktop_config.json\n   ```\n\n### Downloading YOLO Models\n\nBefore using the service, you need to download the YOLO models. The service looks for models in the following directories:\n- The current directory where the service is running\n- A `models` subdirectory\n- Any other directory configured in the `CONFIG[\"model_dirs\"]` variable in server.py\n\nCreate a models directory and download some common models:\n\n```bash\n# Create models directory\nmkdir models\n\n# Download YOLOv8n for basic object detection\ncurl -L https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt -o models/yolov8n.pt\n\n# Download YOLOv8n-seg for segmentation\ncurl -L https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt -o models/yolov8n-seg.pt\n\n# Download YOLOv8n-cls for classification\ncurl -L https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt -o models/yolov8n-cls.pt\n\n# Download YOLOv8n-pose for pose estimation\ncurl -L https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt -o models/yolov8n-pose.pt\n```\n\nFor Windows PowerShell users:\n```powershell\n# Create models directory\nmkdir models\n\n# Download models using Invoke-WebRequest\nInvoke-WebRequest -Uri \"https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt\" -OutFile \"models/yolov8n.pt\"\nInvoke-WebRequest -Uri \"https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt\" -OutFile \"models/yolov8n-seg.pt\"\nInvoke-WebRequest -Uri \"https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt\" -OutFile \"models/yolov8n-cls.pt\"\nInvoke-WebRequest -Uri \"https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt\" -OutFile \"models/yolov8n-pose.pt\"\n```\n\n### Configuring Claude\n\nTo use this service with Claude:\n\n1. For Claude web: Set up the service on your local machine and use the configuration provided by the setup script in your MCP client.\n\n2. For Claude Desktop:\n   - Run the setup script and note the configuration output\n   - Locate your Claude Desktop configuration file (the path is provided in the setup script output)\n   - Add or merge the configuration into your Claude Desktop configuration file\n   - Restart Claude Desktop\n\n## Using YOLO Tools in Claude\n\n### 1. First Check Available Models\n\nAlways check which models are available on your system first:\n\n```\nI'd like to use the YOLO tools. Can you first check which models are available on my system?\n\n\u003cfunction_calls\u003e\n\u003cinvoke name=\"list_available_models\"\u003e\n\u003c/invoke\u003e\n\u003c/function_calls\u003e\n```\n\n### 2. Detecting Objects in an Image\n\nFor analyzing an image file on your computer:\n\n```\nCan you analyze this image file for objects?\n\n\u003cfunction_calls\u003e\n\u003cinvoke name=\"analyze_image_from_path\"\u003e\n\u003cparameter name=\"image_path\"\u003e/path/to/your/image.jpg\u003c/parameter\u003e\n\u003cparameter name=\"confidence\"\u003e0.3\u003c/parameter\u003e\n\u003c/invoke\u003e\n\u003c/function_calls\u003e\n```\n\nYou can also specify a different model:\n\n```\nCan you analyze this image using a different model?\n\n\u003cfunction_calls\u003e\n\u003cinvoke name=\"analyze_image_from_path\"\u003e\n\u003cparameter name=\"image_path\"\u003e/path/to/your/image.jpg\u003c/parameter\u003e\n\u003cparameter name=\"model_name\"\u003eyolov8n.pt\u003c/parameter\u003e\n\u003cparameter name=\"confidence\"\u003e0.4\u003c/parameter\u003e\n\u003c/invoke\u003e\n\u003c/function_calls\u003e\n```\n\n### 3. Running Comprehensive Image Analysis\n\nFor more detailed analysis that combines object detection, classification, and more:\n\n```\nCan you perform a comprehensive analysis on this image?\n\n\u003cfunction_calls\u003e\n\u003cinvoke name=\"comprehensive_image_analysis\"\u003e\n\u003cparameter name=\"image_path\"\u003e/path/to/your/image.jpg\u003c/parameter\u003e\n\u003cparameter name=\"confidence\"\u003e0.3\u003c/parameter\u003e\n\u003c/invoke\u003e\n\u003c/function_calls\u003e\n```\n\n### 4. Image Segmentation\n\nFor identifying object boundaries and creating segmentation masks:\n\n```\nCan you perform image segmentation on this photo?\n\n\u003cfunction_calls\u003e\n\u003cinvoke name=\"segment_objects\"\u003e\n\u003cparameter name=\"image_data\"\u003e/path/to/your/image.jpg\u003c/parameter\u003e\n\u003cparameter name=\"is_path\"\u003etrue\u003c/parameter\u003e\n\u003cparameter name=\"model_name\"\u003eyolov8n-seg.pt\u003c/parameter\u003e\n\u003c/invoke\u003e\n\u003c/function_calls\u003e\n```\n\n### 5. Image Classification\n\nFor classifying the entire image content:\n\n```\nWhat does this image show? Can you classify it?\n\n\u003cfunction_calls\u003e\n\u003cinvoke name=\"classify_image\"\u003e\n\u003cparameter name=\"image_data\"\u003e/path/to/your/image.jpg\u003c/parameter\u003e\n\u003cparameter name=\"is_path\"\u003etrue\u003c/parameter\u003e\n\u003cparameter name=\"model_name\"\u003eyolov8n-cls.pt\u003c/parameter\u003e\n\u003cparameter name=\"top_k\"\u003e5\u003c/parameter\u003e\n\u003c/invoke\u003e\n\u003c/function_calls\u003e\n```\n\n### 6. Using Your Computer's Camera\n\nStart real-time object detection using your computer's camera:\n\n```\nCan you turn on my camera and detect objects in real-time?\n\n\u003cfunction_calls\u003e\n\u003cinvoke name=\"start_camera_detection\"\u003e\n\u003cparameter name=\"model_name\"\u003eyolov8n.pt\u003c/parameter\u003e\n\u003cparameter name=\"confidence\"\u003e0.3\u003c/parameter\u003e\n\u003c/invoke\u003e\n\u003c/function_calls\u003e\n```\n\nGet the latest camera detections:\n\n```\nWhat are you seeing through my camera right now?\n\n\u003cfunction_calls\u003e\n\u003cinvoke name=\"get_camera_detections\"\u003e\n\u003c/invoke\u003e\n\u003c/function_calls\u003e\n```\n\nStop the camera when finished:\n\n```\nPlease turn off the camera.\n\n\u003cfunction_calls\u003e\n\u003cinvoke name=\"stop_camera_detection\"\u003e\n\u003c/invoke\u003e\n\u003c/function_calls\u003e\n```\n\n### 7. Advanced Model Operations\n\n#### Training a Custom Model\n\n```\nI want to train a custom object detection model on my dataset.\n\n\u003cfunction_calls\u003e\n\u003cinvoke name=\"train_model\"\u003e\n\u003cparameter name=\"dataset_path\"\u003e/path/to/your/dataset\u003c/parameter\u003e\n\u003cparameter name=\"model_name\"\u003eyolov8n.pt\u003c/parameter\u003e\n\u003cparameter name=\"epochs\"\u003e50\u003c/parameter\u003e\n\u003c/invoke\u003e\n\u003c/function_calls\u003e\n```\n\n#### Validating a Model\n\n```\nCan you validate the performance of my model on a test dataset?\n\n\u003cfunction_calls\u003e\n\u003cinvoke name=\"validate_model\"\u003e\n\u003cparameter name=\"model_path\"\u003e/path/to/your/trained/model.pt\u003c/parameter\u003e\n\u003cparameter name=\"data_path\"\u003e/path/to/validation/dataset\u003c/parameter\u003e\n\u003c/invoke\u003e\n\u003c/function_calls\u003e\n```\n\n#### Exporting a Model to Different Formats\n\n```\nI need to export my YOLO model to ONNX format.\n\n\u003cfunction_calls\u003e\n\u003cinvoke name=\"export_model\"\u003e\n\u003cparameter name=\"model_path\"\u003e/path/to/your/model.pt\u003c/parameter\u003e\n\u003cparameter name=\"format\"\u003eonnx\u003c/parameter\u003e\n\u003c/invoke\u003e\n\u003c/function_calls\u003e\n```\n\n### 8. Testing Connection\n\nCheck if the YOLO service is running correctly:\n\n```\nIs the YOLO service running correctly?\n\n\u003cfunction_calls\u003e\n\u003cinvoke name=\"test_connection\"\u003e\n\u003c/invoke\u003e\n\u003c/function_calls\u003e\n```\n\n## Troubleshooting\n\n### Camera Issues\n\nIf the camera doesn't work, try different camera IDs:\n\n```\n\u003cfunction_calls\u003e\n\u003cinvoke name=\"start_camera_detection\"\u003e\n\u003cparameter name=\"camera_id\"\u003e1\u003c/parameter\u003e  \u003c!-- Try 0, 1, or 2 --\u003e\n\u003c/invoke\u003e\n\u003c/function_calls\u003e\n```\n\n### Model Not Found\n\nIf a model is not found, make sure you've downloaded it to one of the configured directories:\n\n```\n\u003cfunction_calls\u003e\n\u003cinvoke name=\"get_model_directories\"\u003e\n\u003c/invoke\u003e\n\u003c/function_calls\u003e\n```\n\n### Performance Issues\n\nFor better performance with limited resources, use the smaller models (e.g., yolov8n.pt instead of yolov8x.pt)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FGongRzhe%2FYOLO-MCP-Server","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FGongRzhe%2FYOLO-MCP-Server","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FGongRzhe%2FYOLO-MCP-Server/lists"}