K
Kaggle
Search Kaggle datasets, competitions and notebooks.
·No reviews yet
Share:
About
Auto-generated
Kaggle is a Model Context Protocol server in the Data & Databases category. It lets AI assistants that speak MCP call its tools and read its resources over STDIO.
Example tools
Illustrative tool names — the actual tool set is defined by the server at runtime.
query
Run a read-only SQL query
list_tables
List tables in the connected database
describe_table
Return column info for a table
Screenshots
No screenshots yet.
Frequently Asked Questions
Common questions about Kaggle.
- What does the Kaggle MCP allow me to do?
- This MCP enables searching Kaggle datasets, competitions, and notebooks. It facilitates quick access to public data and machine learning resources directly from your client application.
- How do I install the Kaggle MCP in a client application?
- Installation typically involves adding the MCP's repository URL to your client's settings. For instance, in Cline, you might use a command like 'cline install https://github.com/tarunlnmiit/kaggle-mcp'.
- Does the Kaggle MCP require authentication?
- Yes, this MCP uses API key authentication. You will need to provide a valid Kaggle API key to access its functionalities.
- What are the primary capabilities exposed by this MCP?
- The primary capabilities include searching for various Kaggle entities such as datasets, competitions, and notebooks. It acts as a search interface for Kaggle's extensive content.
- What is a common limitation when using the Kaggle MCP?
- A common limitation is that its functionality is restricted to searching public Kaggle resources. It does not provide capabilities for uploading data or participating in competitions directly through the MCP.
- Is there a cost associated with using the Kaggle MCP?
- The MCP itself is open-source and free, but usage is subject to Kaggle's terms of service. There are no direct costs associated with the MCP client or the underlying Kaggle platform for basic search functionality.
Install Kaggle
Claude Desktop
Add this to claude_desktop_config.json.
{
"mcpServers": {
"kaggle": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-kaggle"
]
}
}
}Cursor
Add this to ~/.cursor/mcp.json.
{
"mcpServers": {
"kaggle": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-kaggle"
]
}
}
}VS Code
Add this to your workspace settings.json.
{
"mcp.servers": {
"kaggle": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-kaggle"
]
}
}
}Reviews
Sign in to leave a review.
No reviews yet. Be the first!
Discussion(0)
No comments yet.