Menu
Search, view, save, and run Kaggle notebooks using Kaggle MCP. Use when exploring public notebooks, pushing code to Kaggle, or managing notebook sessions.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Get competition metadata, data files, and rules using Kaggle MCP. Use when looking up competition details, searching competitions, or fetching competition data file info.
Search, download, and manage Kaggle datasets using Kaggle MCP. Use when finding datasets, checking file structures, or downloading data.
Browse and search Kaggle discussion forums using Kaggle MCP. Use when looking for tips, solutions, or community insights about competitions or datasets.
View and analyze competition leaderboard and submissions using Kaggle MCP. Use when checking rankings, scores, or submission history.
Submit to a Kaggle competition (code/notebook submission or file upload). Use when submitting predictions or notebooks to a competition.
Initialize project and set up competition environment (all-in-one). Use when starting a new Kaggle/atmaCup competition project or when user invokes /setup.
| name | kaggle-notebooks |
| description | Search, view, save, and run Kaggle notebooks using Kaggle MCP. Use when exploring public notebooks, pushing code to Kaggle, or managing notebook sessions. |
| argument-hint | ["search-term or username/notebook-slug"] |
Manage Kaggle notebooks using the Kaggle MCP server.
Target: $ARGUMENTS
mcp__kaggle__search_notebooks({
request: {
hasSearch: true,
search: "<search-term>",
sortBy: "Hotness",
hasPageSize: true,
pageSize: 10
}
})
Search by competition:
mcp__kaggle__search_notebooks({
request: {
hasCompetition: true,
competition: "<competition-name>",
sortBy: "VoteCount",
hasPageSize: true,
pageSize: 10
}
})
Sort options: Hotness, VoteCount, DateCreated, DateRun, Relevance, CommentCount, ViewCount
Language filter: python, r, sqlite, julia, all
mcp__kaggle__get_notebook_info({
request: {
userName: "<owner-username>",
kernelSlug: "<notebook-slug>"
}
})
Returns metadata (title, language, data sources) and blob (source code).
Push local code to Kaggle and execute:
mcp__kaggle__save_notebook({
request: {
slug: "<username>/<notebook-slug>",
newTitle: "<Notebook Title>",
hasText: true,
text: "<source-code>",
hasLanguage: true,
language: "python",
hasKernelType: true,
kernelType: "notebook",
isPrivate: true,
hasEnableInternet: true,
enableInternet: false,
competitionDataSourcesSetter: ["<competition-name>"],
datasetDataSourcesSetter: ["<owner>/<dataset>"],
modelDataSourcesSetter: ["<owner>/<model>/<framework>/<variation>"]
}
})
Machine shapes: Use machineShape parameter (e.g., "gpu-t4", "gpu-p100", "tpu")
mcp__kaggle__get_notebook_session_status({
request: {
userName: "<username>",
kernelSlug: "<notebook-slug>"
}
})
Status values: QUEUED, RUNNING, COMPLETE, ERROR, CANCEL_REQUESTED
List output files:
mcp__kaggle__list_notebook_session_output({
request: {
userName: "<username>",
kernelSlug: "<notebook-slug>"
}
})
Download output:
mcp__kaggle__download_notebook_output({
request: {
ownerSlug: "<username>",
kernelSlug: "<notebook-slug>"
}
})
mcp__kaggle__list_notebook_files({
request: {
userName: "<username>",
kernelSlug: "<notebook-slug>"
}
})
mcp__kaggle__cancel_notebook_session({
request: { kernelSessionId: <session-id> }
})
username/notebook-slugcompetitionDataSourcesSetterenableGpu and enableTpu are deprecated; use machineShape insteadkernelType: "notebook" or "script"