Built by Metorial, the integration platform for agentic AI.
Create or update a Kaggle notebook (kernel) and execute it. Push source code to run as a notebook or script. The execution is asynchronous — use "Get Notebook Details" to check the run status afterward.
Retrieve detailed information about a specific Kaggle dataset including metadata and file listing. Provide the dataset reference in "owner/dataset" format (e.g., "zillow/zecon").
Create a new Kaggle dataset or publish a new version of an existing dataset. For new datasets, provide a title and file tokens obtained from file uploads. For new versions, specify the existing dataset reference and version notes.
Search and list Kaggle models. Find models by keyword, owner, and sort by various criteria. Models support multiple variations (e.g., different frameworks like TensorFlow, PyTorch) and each variation can have multiple versions.
Retrieve detailed information about a specific Kaggle competition, including its data files, leaderboard, and your submission history. Provide the competition slug (e.g., "titanic") to get comprehensive details.
Search and list Kaggle datasets with comprehensive filtering. Find datasets by keyword, file type, license, size range, and tags. Sort results by hotness, votes, updated date, relevance, or size.
Create, update, or delete a Kaggle model. Use this tool to manage top-level model resources. For managing model variations and versions, use the "Manage Model Variation" tool instead.
Retrieve detailed information about a Kaggle model and optionally a specific variation. Provide the model reference as "owner/model-slug" and optionally a framework and variation slug to get a specific instance.
Search and list Kaggle competitions with filtering options. Find competitions by keyword, category (featured, research, playground, etc.), and sort by various criteria like deadline, recently created, or number of teams.
Create, update, or delete a model variation (instance) and manage variation versions. A variation represents a specific framework implementation (e.g., TensorFlow, PyTorch) of a model. You can also create new versions of existing variations.
Retrieve source code and execution details for a specific Kaggle notebook (kernel). Optionally fetch execution output and run status. Provide the notebook reference as "username/kernel-slug".
Search and list Kaggle notebooks (kernels) with comprehensive filtering. Find notebooks by keyword, dataset, competition, language, type, and author. Sort by hotness, date created, date run, relevance, votes, or views.
Prepare a downloadable tar.gz archive of a specific Kaggle model variation version. Use get_model_details to discover models and variations.
Prepare a downloadable ZIP archive of a Kaggle dataset, or download one named file. Use get_dataset_details to discover file names and dataset versions.
Prepare downloadable competition data as a ZIP archive or one named file. Your account must have accepted the competition rules. Use get_competition_details to discover file names.