MCP Server Scikit Learn

🚀 mcp-server-scikit-learn: MCP Server for Scikit-learn

This is a Model Context Protocol (MCP) server for Scikit-learn, providing a standard interface for interacting with Scikit-learn models and datasets.

🚀 Quick Start

✨ Features

• Train and evaluate Scikit-learn models.
• Handle datasets and data preprocessing.
• Persist and load models.
• Perform feature engineering and selection.
• Calculate model evaluation metrics.
• Conduct cross-validation and hyperparameter tuning.

📦 Installation

This project is not yet configured for temporary environments (e.g., for use with uvx). To run this project locally, clone the repository:

git clone https://github.com/yourusername/mcp-server-scikit-learn.git
cd mcp-server-scikit-learn

You can start the MCP Inspector via npm:

npx @modelcontextprotocol/inspector uv --directory=src/mcp_server_scikit_learn run mcp-server-scikit-learn

After startup, the inspector will display a URL. You can open this URL in your browser to start debugging.

Alternatively, add this tool as an MCP server:

{
  "scikit-learn": {
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/mcp-server-scikit-learn",
      "run",
      "mcp-server-scikit-learn"
    ]
  }
}

💻 Usage Examples

Basic Usage

To start development:

1. Create and activate a virtual environment:

python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

2. Install dependencies:

pip install -e ".[dev]"

3. Run tests:

pytest -s -v tests/

📄 License

License