Kaggle is an online community platform for data scientists and machine learning practitioners that allows users to find and publish datasets, explore and build models in a web-based data science environment, work with other data scientists and machine learning engineers, and enter competitions to solve data science challenges.
Why this server?
Provides tools for retrieving the full context of a Kaggle competition: key facts and a brief (metric, deadlines, limits, submission format, external-data rule), sections (overview, evaluation, rules, data, leaderboard, timeline, prizes), discussion topics with top comments and solution write-ups (list, keyword search, fetch one), top public notebooks by votes with code and markdown (outputs stripped), and leaderboard entries. Also supports several competitions via caching/fetching and a live `get_whats_new` tool that reports forum topics created or commented on since the last fetch.
Why this server?
Routes training jobs to free Kaggle GPUs (P100 or 2xT4), tracks Kaggle's 30 GPU-hours/week quota and 12h session cap, streams logs, and reroutes jobs when Kaggle is rate-limited or a session ends.
Why this server?
Provides tools for interacting with the Kaggle API, enabling AI agents to manage competitions, datasets, kernels, models, benchmarks, and discussions on Kaggle.
Why this server?
Provides integration with Kaggle as a compute worker for the GPU pool, allowing agents to submit jobs, track execution, and collect artifacts and metrics from Kaggle kernels.
Why this server?
Provides tools for searching and downloading Kaggle datasets, and generating prompts for exploratory data analysis (EDA) notebooks on specific datasets.
Why this server?
Enables submitting compute jobs to Kaggle workers with hardware-aware scheduling, using authorized credentials, and collecting artifacts and metrics from kernel runs.
Why this server?
Integrates with Kaggle API to create, run, and manage Kaggle notebooks; search datasets and competitions; download outputs; and monitor execution status.
Why this server?
The MCP Server provides examples of data exploration using Kaggle datasets, demonstrating how to analyze and visualize large datasets such as USA Real Estate and UK Weather History.
Why this server?
Provides tools for interacting with Kaggle's API, enabling AI agents to manage competitions, datasets, kernels, models, discussions, and leaderboards with safety-first features like preview-commit confirm tokens and submission budgeting.