Tidymodels MCP

🚀 Tidymodels MCP Server

A Model Context Protocol (MCP) server that provides tools and resources for working with the tidymodels ecosystem in R.

🚀 Quick Start

The Tidymodels MCP Server offers a range of functionalities to interact with the tidymodels ecosystem. It can be paired with tools like Cline.bot and Claude Desktop to provide comprehensive information about tidymodels.

✨ Features

• Package Listing: List all packages in the tidymodels ecosystem.
• Package Details: Provide detailed information about specific packages.
• Function Search: Search for R functions within tidymodels packages.
• Code Template Generation: Generate template code for common tidymodels tasks.
• Issue Search: Search for issues in tidymodels repositories.

📦 Installation

Prerequisites

• Node.js (v14 or higher)
• npm

Setup

1. Clone this repository:

   git clone https://github.com/yourusername/tidymodels-mcp.git
   cd tidymodels-mcp
   

2. Install dependencies:

   npm install
   

📚 Documentation

Configuration

Environment Variables

To configure the MCP server, set the following environment variables:

• PORT: Specify the port on which the server runs (default is 3000).
• LOG_LEVEL: Specify the log level (values can be 'debug', 'info', 'warning', 'error', or 'none').

For example, use a .env file:

PORT=3001
LOG_LEVEL=info

Configuration File

Create a config.json file to specify the configuration:

{
  "port": 3000,
  "logLevel": "info",
  "repositories": [
    "tidymodels/tidymodels",
    "tidymodels/parsnip"
  ]
}

Usage

• Start the server:

npm start

• Access the documentation:

npm run docs

• Run tests:

npm test

Development

Project Structure

• js/: Contains the JavaScript/Node.js server implementation.
• src/: Contains TypeScript source files (if using TypeScript).
• build/: Build output directory.

Build Source Code

If you make changes to the TypeScript files, you can rebuild the server by running:

npm run build

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

• The tidymodels team for their excellent R packages.
• Model Context Protocol (MCP) for its enhanced AI capabilities.