Kaggle-MCP Documentation

Kaggle-MCP connects Claude AI to the Kaggle API through the Model Context Protocol (MCP), enabling competition, dataset, and kernel operations through the AI interface.

Overview

Kaggle-MCP is a bridge between Claude AI and the Kaggle platform, allowing you to:

• Access and manipulate Kaggle competitions
• Search and download datasets
• Find and use kernels/notebooks
• Work with models and their instances

This tool enables a seamless AI-integrated workflow for data science and machine learning tasks on Kaggle.

Quick Links

• Installation Guide
• Authentication
• Competitions API
• Datasets API
• Kernels API
• Models API
• Configuration
• Examples

Getting Started

To get started with Kaggle-MCP:

1. Install the package (see Installation)
2. Configure Claude Desktop to use the MCP server
3. Authenticate with your Kaggle credentials
4. Start using the tools through Claude AI

Requirements

• Python 3.8 or newer
• Claude Desktop or API access
• Kaggle account with API credentials
• MCP Python SDK 1.6.0+

Project Information

• GitHub Repository
• License: MIT