OpenCV

Installation

pip install opencv-mcp-server

For development:

git clone https://github.com/yourusername/opencv-mcp-server.git
cd opencv-mcp-server\n\n# Create a virtual environment
python -m venv .venv
source .venv/bin/activate\n\n# On Windows: .venv\Scripts\activate\n\n# Install dependencies
pip install -e .

Usage## Use in Claude Desktop

Add to your Claude Desktop configuration:

{
  "tools": {
    "opencv": {
      "command": "uvx",
      "args": [
        "opencv-mcp-server"
      ]
    }
  }
}

Basic Python Usage

from opencv_mcp_server import opencv_client\n\n# Initialize client
client = opencv_client.OpenCVClient()\n\n# Use tools
result = client.resize_image(image_path="input.jpg", width=800, height=600)

Configuration

The server can be configured using environment variables:

• MCP_TRANSPORT: Transport method (default: "stdio")
• OPENCV_DNN_MODELS_DIR: Directory for storing DNN models (default: "models")
• CV_HAAR_CASCADE_DIR: Directory for storing Haar cascade files (optional)

Available Tools

The OpenCV MCP Server provides a wide range of computer vision tools organized into four categories:

• Image Basics
• Image Processing
• Computer Vision
• Video Processing

License

MIT License - See the LICENSE file for details.