Kaggle MCP server for AI agents

Kaggle-MCP connects Claude AI to the Kaggle API through the Model Context Protocol, allowing you to interact with Kaggle competitions, datasets, and kernels directly through Claude's interface. This tool enables seamless access to Kaggle's resources without leaving your AI assistant.

Installation Options

Quick Installation

macOS / Linux

# Install with a single command
curl -LsSf https://raw.githubusercontent.com/54yyyu/kaggle-mcp/main/install.sh | sh

Windows

# Download and run the installer
powershell -c "Invoke-WebRequest -Uri https://raw.githubusercontent.com/54yyyu/kaggle-mcp/main/install.ps1 -OutFile install.ps1; .\install.ps1"

Manual Installation

# Install with pip
pip install git+https://github.com/54yyyu/kaggle-mcp.git

# Or better, install with uv
uv pip install git+https://github.com/54yyyu/kaggle-mcp.git

Configuration

After installation, run the setup utility to configure Claude Desktop:

kaggle-mcp-setup

This will locate and update your Claude Desktop configuration file automatically.

Manual Configuration

If you prefer, you can manually add the following to your Claude Desktop configuration file:

{
  "mcpServers": {
    "kaggle": {
      "command": "kaggle-mcp"
    }
  }
}

Configuration file locations:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

Setting Up Kaggle API Credentials

To use Kaggle-MCP, you need to configure your Kaggle API credentials:

Go to your Kaggle account settings
In the API section, click "Create New API Token"
This will download a kaggle.json file with your credentials
Move this file to ~/.kaggle/kaggle.json (create the directory if needed)
Set the correct permissions: chmod 600 ~/.kaggle/kaggle.json

Alternatively, you can authenticate directly through Claude using the authenticate() tool with your username and API key.

Using Kaggle-MCP with Claude

Available Features

Authentication: Securely authenticate with your Kaggle credentials
Competitions: Browse, search, and download data from Kaggle competitions
Datasets: Find, explore, and download datasets from Kaggle
Kernels: Search for and analyze Kaggle notebooks/kernels
Models: Access pre-trained models available on Kaggle

Example Commands

You can ask Claude to:

"Authenticate with Kaggle using my username 'username' and key 'apikey'"
"List active Kaggle competitions"
"Show me the top 10 competitors on the Titanic leaderboard"
"Find datasets about climate change"
"Download the Boston housing dataset"
"Search for kernels about sentiment analysis"

Use Cases

Competition Research: Quickly access competition details, data, and leaderboards
Dataset Discovery: Find and download datasets for analysis projects
Learning Resources: Locate relevant kernels and notebooks for specific topics
Model Discovery: Find pre-trained models for various machine learning tasks

System Requirements

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

For more detailed documentation on available tools and their usage, visit stevenyuyy.us/kaggle-mcp.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "kaggle" '{"command":"kaggle-mcp"}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "kaggle": {
            "command": "kaggle-mcp"
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "kaggle": {
            "command": "kaggle-mcp"
        }
    }
}

3. Restart Claude Desktop for the changes to take effect