kaggle-mcp
If you are the rightful owner of kaggle-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
The Kaggle MCP Server is a Model Context Protocol server built using the fastmcp library, designed to interact with the Kaggle API for dataset management and EDA notebook generation.
The Kaggle MCP Server is a specialized server application that leverages the Model Context Protocol (MCP) to facilitate interactions with the Kaggle API. It is built using the fastmcp library and provides tools for searching and downloading datasets from Kaggle, as well as generating prompts for Exploratory Data Analysis (EDA) notebooks. The server is designed to be easily set up and run, with support for environment variables and Docker for deployment. It is particularly useful for data scientists and AI developers who need to quickly access and analyze datasets from Kaggle. The server can be integrated with AI agents or MCP clients to automate dataset management and EDA tasks.
Features
- Dataset Search: Allows users to search for datasets on Kaggle using a query string, returning a list of matching datasets.
- Dataset Download: Enables downloading and unzipping of specific Kaggle datasets using their reference identifiers.
- EDA Notebook Generation: Generates prompts for AI models to create basic EDA notebooks, including data loading, visualization, and statistics.
Tools
search_kaggle_datasets
Searches for datasets on Kaggle matching the provided query string.
download_kaggle_dataset
Downloads and unzips files for a specific Kaggle dataset.
generate_eda_notebook
Generates a prompt for creating an EDA notebook for a specified Kaggle dataset.
