Kaggle MCP

🚀 Kaggle MCP Server

A Model Context Protocol (MCP) server for interacting with Kaggle competitions via Claude or other compatible AI assistants.

🚀 Quick Start

This is a Model Context Protocol (MCP) server that enables interaction with Kaggle competitions through Claude or other compatible AI assistants.

✨ Features

• Dataset Operations: Browse, search, download, and analyze datasets on Kaggle.
• Notebook Integration: Work with Kaggle notebooks directly from an AI assistant.
• User Management: View profile information and check competition rankings.
• Competition Analysis: Obtain detailed competition metrics and leaderboard insights.

📚 Documentation

Want to explore the full potential of this server? Check out the detailed article:

AI-Powered Data Science Revolution: How the Kaggle MCP Server Transforms AI Capabilities

📦 Installation

Prerequisites

• Node.js version 16 or higher
• TypeScript
• Installed Kaggle CLI (pip install kaggle)
• Configured Kaggle API credentials

Authentication Setup

There are two ways to authenticate with the Kaggle API:

Option 1: Use the kaggle.json file (standard method)

1. Install the Kaggle CLI:

pip install kaggle

2. Visit https://www.kaggle.com/account and click "Create New API Token".
3. This will download a kaggle.json file containing your credentials.
4. Create a .kaggle folder in your home directory (if it doesn't exist):

# For Linux/Mac
mkdir -p ~/.kaggle

# For Windows (PowerShell)
New-Item -ItemType Directory -Force -Path "$HOME\.kaggle"

5. Move the downloaded kaggle.json file to the .kaggle directory:

# For Linux/Mac
mv ~/Downloads/kaggle.json ~/.kaggle/
chmod 600 ~/.kaggle/kaggle.json  # Set permissions

# For Windows (PowerShell)
Move-Item -Path "$HOME\Downloads\kaggle.json" -Destination "$HOME\.kaggle\kaggle.json"

Option 2: Use Claude Desktop configuration (simpler)

You can directly add your Kaggle credentials to the claude_desktop_config.json file:

{
  "mcpServers": {
    "kaggle": {
      "command": "node",
      "args": ["/path/to/build/index.js"],
      "env": {
        "KAGGLE_USERNAME": "Your Kaggle Username",
        "KAGGLE_KEY": "Your Kaggle API Key"
      }
    }
  }
}

Replace Your Kaggle Username and Your Kaggle API Key.

Clone the Repository

Clone the repository from GitHub:

git clone https://github.com/yourusername/kaggle-mcp-server.git
cd kaggle-mcp-server
npm install

💻 Usage Examples

Basic Usage

Initialize the server

node index.js

Submit to a competition

curl -X POST http://localhost:3000/api/submit \
  -F "file=@your_predictions.csv" \
  -F "competition_id=abc123"

All Features Now Available

All previously listed "Coming Soon" features are now included in the feature-complete branch, which includes:

• Dataset Operations: Browse, search, download, and analyze datasets on Kaggle.
• Notebook Integration: Work with Kaggle notebooks directly from an AI assistant.
• User Management: View profile information and check competition rankings.
• Competition Analysis: Obtain detailed competition metrics and leaderboard insights.

Please refer to the feature-complete branch for the latest and most comprehensive implementation of the Kaggle MCP server.

📄 License

MIT