Kaggle MCP
Connects Claude AI to the Kaggle API through the Model Context Protocol, enabling users to browse competitions, search and download datasets, analyze kernels, and access pre-trained models through natural language interactions.
What is Kaggle MCP?
Kaggle MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to connects claude ai to the kaggle api through the model context protocol, enabling users to browse competitions, search and download datasets, analyze kernels, and access pre-trained models through nat...
Connects Claude AI to the Kaggle API through the Model Context Protocol, enabling users to browse competitions, search and download datasets, analyze kernels, and access pre-trained models through natural language interactions.
This server falls under the Data Science & ML and Analytics categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Connects Claude AI to the Kaggle API through the Model Conte
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx kaggle-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Kaggle MCP
Kaggle-MCP connects Claude AI to the Kaggle API through the Model Context Protocol, enabling natural language access to Kaggle competitions, datasets, kernels (notebooks), and pre-trained models. Instead of navigating Kaggle's website or writing API scripts, you can ask Claude to find a competition, download its data, explore top kernels, or browse available models — all within your chat session. Data scientists and ML practitioners use it to accelerate dataset discovery and competition research without leaving their AI workflow.
Prerequisites
- Python 3.8 or newer installed
- A Kaggle account with API credentials — go to https://www.kaggle.com/settings/account, click 'Create New API Token', and place the downloaded kaggle.json at ~/.kaggle/kaggle.json with permissions set to 600
- MCP Python SDK 1.6.0 or higher
- Claude Desktop or another MCP-compatible client
Install Kaggle-MCP
Install from the GitHub repository using pip or uv. A setup utility (kaggle-mcp-setup) is included to auto-configure Claude Desktop.
# With pip
pip install git+https://github.com/54yyyu/kaggle-mcp.git
# Or with uv (recommended)
uv pip install git+https://github.com/54yyyu/kaggle-mcp.gitPlace your Kaggle API credentials
Move the kaggle.json downloaded from your Kaggle account settings into the expected location and restrict its permissions.
mkdir -p ~/.kaggle
mv ~/Downloads/kaggle.json ~/.kaggle/kaggle.json
chmod 600 ~/.kaggle/kaggle.jsonRun the setup utility to configure Claude Desktop automatically
kaggle-mcp-setup locates your Claude Desktop config file and adds the mcpServers entry for you. Alternatively, add the entry manually as shown in the examples section.
kaggle-mcp-setupRestart Claude Desktop
After the configuration is written, restart Claude Desktop so it picks up the new server entry.
Authenticate and start exploring Kaggle
Claude will use the credentials from ~/.kaggle/kaggle.json automatically. You can also authenticate inline with the authenticate tool if you want to use a different account.
Kaggle MCP Examples
Client configuration
Manual configuration for claude_desktop_config.json if you prefer not to use the setup utility.
{
"mcpServers": {
"kaggle": {
"command": "kaggle-mcp"
}
}
}Prompts to try
Use these prompts with Claude Desktop to browse and download Kaggle resources.
- "List the currently active Kaggle competitions"
- "Show me the top 10 entries on the Titanic competition leaderboard"
- "Find datasets about climate change with more than 1000 downloads"
- "Download the Boston housing dataset"
- "Search for kernels about transformer fine-tuning in NLP"
- "Show me pre-trained image classification models available on Kaggle"Troubleshooting Kaggle MCP
401 Unauthorized when calling Kaggle tools
Verify that ~/.kaggle/kaggle.json exists, is readable (chmod 600), and contains valid 'username' and 'key' fields. You can also pass credentials directly by asking Claude to call the authenticate tool with your username and API key.
'kaggle-mcp' command not found after installation
The console script may not be on your PATH. Run 'which kaggle-mcp' or 'pip show kaggle-mcp' to locate the install directory, then add it to PATH. Using uv or pipx ensures the script is properly symlinked.
Dataset download is slow or fails midway
Large Kaggle datasets can take time. Ensure you have accepted the dataset's terms of use on the Kaggle website — some datasets require explicit acceptance before the API will serve them.
Frequently Asked Questions about Kaggle MCP
What is Kaggle MCP?
Kaggle MCP is a Model Context Protocol (MCP) server that connects claude ai to the kaggle api through the model context protocol, enabling users to browse competitions, search and download datasets, analyze kernels, and access pre-trained models through natural language interactions. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Kaggle MCP?
Follow the installation instructions on the Kaggle MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Kaggle MCP?
Kaggle MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Kaggle MCP free to use?
Yes, Kaggle MCP is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Kaggle MCP Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Kaggle MCP? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Kaggle MCP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Kaggle MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.