Skip to main content
Kaggle logo
  • Category: artificial intelligence
  • Auth: API_KEY
  • Composio-managed OAuth available? N/A
  • Tools: 35
  • Triggers: 0
  • Slug: KAGGLE
  • Version: 20261101_00

Tools

Slug: KAGGLE_COMPETITION_DOWNLOAD_FILESDownloads all data files for a Kaggle competition as a single zip archive. Returns a downloadable file object. Note: You must have accepted the competition’s rules on Kaggle’s website before downloading (403 error if not accepted).

Input Parameters

string
required
Competition URL slug (identifier). Find this in the competition’s URL: kaggle.com/competitions/{slug}
string
Deprecated. Local download paths are no longer returned.
boolean
Deprecated. Local file caching is no longer used.
boolean
Reserved for future use. Currently has no effect on download behavior.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_COMPETITION_SUBMITSubmit an entry to a Kaggle competition using a previously uploaded file. Prerequisites: 1. You must have accepted the competition rules on Kaggle’s website 2. You must have uploaded your submission file and obtained a blob_file_tokens (use Kaggle’s file upload API endpoint first) This action performs the final submission step after file upload. The blob token identifies your uploaded file and associates it with your competition submission.

Input Parameters

string
required
Competition slug (URL name) from the competition URL. For example, use ‘titanic’ for kaggle.com/c/titanic. You must have accepted the competition rules before submitting.
string
required
File upload token obtained from Kaggle’s blob upload API. This token is returned when you upload your submission file using the Kaggle API’s upload endpoint (typically /competitions/submissions/upload). The token identifies the location of your uploaded submission file on Kaggle’s servers.
string
required
Brief description or message for this submission (e.g., what changes you made, model version, etc.). This helps you track different submissions.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_CONFIG_DIRTool to retrieve the directory of the Kaggle API configuration file. Use when you need to locate the directory containing your kaggle.json credentials.

Input Parameters

boolean
Prefer XDG config home path on POSIX
string
Force platform branch: ‘windows’ or ‘posix’. If not set, auto-detect.
boolean
Skip CLI, compute directory using environment/platform defaults.
string
Override XDG_CONFIG_HOME base directory for fallback computation.
string
Override directory to use as Kaggle config directory

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_CONFIG_INITInitialize local Kaggle client configuration using the CLI or, if it fails, a kaggle.json fallback in the configured or default directory. The fallback leaves an existing file unchanged and may create a file with empty credentials.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_CONFIG_KEYSTool to list local Kaggle API configuration keys. Use when you need to see which configuration options are set without revealing values.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_CONFIG_PATHTool to retrieve local Kaggle API configuration file path. Use when you need to know the location of the Kaggle config before operations.

Input Parameters

boolean
Prefer XDG config home path on POSIX
string
Force platform branch: ‘windows’ or ‘posix’. If not set, auto-detect.
boolean
Skip CLI, compute path using environment/platform defaults.
string
Override XDG_CONFIG_HOME base directory for fallback computation.
string
Override directory to use for kaggle.json

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_CONFIG_RESETReset local Kaggle CLI configuration by clearing the competition, path, and proxy settings. An invalid local configuration file may be replaced, losing other settings and credentials.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_CONFIG_SETSet a local Kaggle CLI configuration parameter to a supplied value. The supported parameters are competition, path, and proxy. An invalid local configuration file may be replaced, losing other settings and credentials.

Input Parameters

string ("competition" | "path" | "proxy")
required
Configuration parameter to set. Must be one of ‘competition’, ‘path’, or ‘proxy’.
string
required
Value to assign to the configuration parameter.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_CONFIG_UNSETUnset a local Kaggle CLI configuration parameter: competition, path, or proxy. An invalid local configuration file may be replaced, losing other settings and credentials.

Input Parameters

string ("competition" | "path" | "proxy")
required
Configuration parameter to unset. Must be one of ‘competition’, ‘path’, or ‘proxy’.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_CONFIG_VIEWView local Kaggle API credentials and configuration settings. This action reads Kaggle configuration from local sources (does NOT make API calls to Kaggle). Configuration is retrieved in the following precedence order: 1. kaggle.json file (from KAGGLE_CONFIG_DIR env var, ~/.config/kaggle/, or ~/.kaggle/) 2. ‘kaggle config view’ CLI output (for proxy/path settings) 3. Environment variables (KAGGLE_USERNAME, KAGGLE_KEY) 4. Authorization header from metadata Use this action to: - Verify Kaggle credentials are configured before making API calls - Check current proxy settings - Debug authentication issues Returns empty strings for username/key if no credentials are found; use KAGGLE_CONFIG_INIT to set up credentials first. Note: username and key are independent — an empty username field does not indicate missing or invalid credentials. WARNING: This action returns sensitive API key data in plain text.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_DATASET_CREATECreate a new Kaggle dataset with metadata. IMPORTANT: Dataset creation requires at least one data file. Ensure files are uploaded before calling this action. The ‘id’ field must use your authenticated Kaggle username as the owner. Returns the creation status and any message from the Kaggle API.

Input Parameters

string
required
Dataset identifier in the form ‘<owner>/<dataset-slug>’. The owner must be your authenticated Kaggle username (or an organization you belong to). The dataset-slug must be lowercase, 3-50 characters, using only letters, numbers, and hyphens.
array
List of files already uploaded via a separate Kaggle file upload API call. Each entry references a previously uploaded file by name. NOTE: At least one file (via ‘files’ or physical upload) is typically required for successful dataset creation.
string
required
Dataset title shown on Kaggle.
array
Tags to improve discovery.
array
required
Provide exactly one license entry.
string
Brief subtitle for the dataset card.
array
List of resource entries describing the dataset files and their metadata. Not required, but useful for providing file descriptions and schemas.
string
Full Markdown-formatted description.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_DATASET_INITTool to initialize a dataset-metadata.json file in a local folder. Use when preparing a dataset folder before uploading to Kaggle.

Input Parameters

string
Folder path to initialize dataset-metadata.json; defaults to current working directory.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_DATASET_LIST_FILESTool to list files in a Kaggle dataset. Use when you need to retrieve paginated file listings by owner and dataset slugs, with optional version and paging controls.

Input Parameters

integer
Number of items per page (default 20).
string
required
Owner of the dataset (username or organization).
string
Token for pagination of results.
string
required
Slug (name) of the dataset.
string
Specific dataset version number, e.g., ‘1’.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_DATASET_STATUSCheck the processing status of a Kaggle dataset after creation or version update. This endpoint is used to monitor datasets that are currently being processed by Kaggle’s servers. It returns status information for datasets that are actively uploading, processing, or experiencing errors. For already-published datasets, this endpoint typically returns 404 (Not Found), which is expected behavior. Use this tool immediately after creating a new dataset (KAGGLE_DATASET_CREATE) or updating an existing dataset version (KAGGLE_DATASET_VERSION) to check when the dataset becomes ready. Poll this endpoint periodically until the status indicates completion or error.

Input Parameters

string
required
Owner username or organization name of the dataset. This is the first part of the dataset identifier (e.g., ‘username’ in ‘username/dataset-name’).
string
required
URL-friendly slug (identifier) of the dataset. This is the second part of the dataset identifier (e.g., ‘dataset-name’ in ‘username/dataset-name’).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_DATASET_VERSIONCreate a new version of an existing Kaggle dataset using previously uploaded files and version notes, optionally deleting all previous versions. API errors are returned in the result.

Input Parameters

array
required
List of files to include in this version. Each file must reference an upload token obtained from a prior file upload to Kaggle’s storage. At least one file is required.
string
Optional new subtitle for the dataset
string
required
Username or organization slug that owns the dataset. You must have edit permissions for this dataset.
string
Optional new description for the dataset
array
Optional list of category IDs to tag the dataset with
string
required
URL-friendly slug identifier of the dataset to create a new version for
string
required
Notes describing changes in the new dataset version
boolean
Whether to convert tabular data to CSV
boolean
Whether to delete all previous versions when creating this new one

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_DOWNLOAD_COMPETITION_FILETool to download a specific data file from a Kaggle competition. Use when you need to retrieve a single file from a competition by specifying the competition slug and filename. Note: You must have accepted the competition’s rules on Kaggle’s website before downloading.

Input Parameters

string
required
Competition URL slug (identifier). Find this in the competition’s URL: kaggle.com/competitions/{slug}
string
required
Name of the specific competition data file to download (e.g., ‘train.csv’, ‘test.csv’).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_DOWNLOAD_COMPETITION_LEADERBOARDTool to download the entire competition leaderboard as a CSV file packaged in a ZIP archive. Use when you need to analyze or review competition standings and scores.

Input Parameters

string
required
Competition name or URL slug (identifier). Find this in the competition’s URL: kaggle.com/competitions/{slug}
string
Deprecated. Local download paths are no longer returned.
boolean
Deprecated. Local file caching is no longer used.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_DOWNLOAD_DATASETTool to download all files from a Kaggle dataset as a zip archive. Supports downloading specific versions by providing the dataset_version_number parameter.

Input Parameters

string
required
Owner of the dataset (username or organization).
string
required
Slug (name) of the dataset.
string
Specific dataset version number to download. If not specified, downloads the latest version.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_DOWNLOAD_DATASET_FILETool to download a specific file from a Kaggle dataset. Use when you need to retrieve a single file from a dataset by specifying the owner, dataset, and filename.

Input Parameters

string
required
Name of the file to download from the dataset.
string
required
Dataset owner username or organization name.
string
required
Dataset slug (name identifier).
string
Specific dataset version number to download. If not specified, downloads from the latest version.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_GENERATE_COMPETITION_SUBMISSION_URLTool to generate a pre-signed URL for uploading competition submission files. Use this before uploading your submission file to Kaggle. This action generates a temporary upload URL and token for submitting to a competition. You must provide the competition ID, file size, and last modified timestamp. After obtaining the URL, upload your submission file to the createUrl, then use the token to finalize the submission.

Input Parameters

string
required
Competition name, as it appears in the competition’s URL. For example, use ‘titanic’ for kaggle.com/c/titanic. You must have accepted the competition rules before generating submission URLs.
string
Competition submission file name. Typically a CSV file containing your predictions. If not provided, a default name may be assigned.
integer
required
Content length of the submission file in bytes. This is the size of the file you plan to upload.
integer
required
Last modified date of the submission file in seconds since epoch (Unix timestamp) in UTC. Use the file’s last modified timestamp.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_GET_DATASET_METADATATool to get comprehensive metadata for a Kaggle dataset including title, description, licenses, and tags. Use when you need detailed information about a dataset’s structure, schema, or properties.

Input Parameters

string
required
Owner username or organization name of the dataset. This is the first part of the dataset identifier (e.g., ‘uciml’ in ‘uciml/iris’).
string
required
URL-friendly slug (identifier) of the dataset. This is the second part of the dataset identifier (e.g., ‘iris’ in ‘uciml/iris’).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_GET_MODELTool to get a Kaggle model’s details including metadata and description. Use when you need information about a specific model on Kaggle.

Input Parameters

string
required
Model name/slug. This is the second part of the model identifier (e.g., ‘bert’ in ‘google/bert’).
string
required
Model owner username or organization name. This is the first part of the model identifier (e.g., ‘google’ in ‘google/bert’).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_GET_MODEL_INSTANCETool to get details for a specific Kaggle model instance (variation). Returns metadata including overview, usage instructions, download URL, version information, and license details. Use when you need to inspect or retrieve information about a specific model variation before downloading or using it.

Input Parameters

string
required
Framework name for this model variation (e.g., TensorFlow2, PyTorch, Jax, TfLite, TfJs, Coral).
string
required
Model name/slug. This is the second part of the model identifier (e.g., ‘bert’ in ‘tensorflow/bert’).
string
required
Model owner username or organization name. This is the first part of the model identifier (e.g., ‘tensorflow’ in ‘tensorflow/bert’).
string
required
Variation name/slug. This identifies the specific model instance or version (e.g., ‘bert-en-uncased-l-12-h-768-a-12’).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_KERNEL_INITInitialize a kernel-metadata.json template file in a specified folder. This file is required before pushing/uploading a kernel to Kaggle. The template includes default values for kernel configuration (language, kernel_type, GPU settings, etc.) that can be customized before pushing. Use this when setting up a new Kaggle kernel locally.

Input Parameters

string
Folder path where kernel-metadata.json will be created. Use ’.’ for current directory or provide an absolute/relative path.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_KERNEL_OUTPUTDownload a Kaggle kernel’s output as a downloadable archive.

Input Parameters

string
Deprecated. Local download paths are no longer returned.
boolean
Deprecated. Local file caching is no longer used.
string
required
Owner of the kernel.
string
required
Slug name of the kernel.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_KERNELS_STATUSGet the execution status of a Kaggle kernel to monitor a run. The response may include timestamps and an output URL; HTTP request failures are returned as status ‘error’ with an error message, which does not necessarily indicate a failed kernel run.

Input Parameters

string
required
Username of the kernel owner (typically your Kaggle username for your own kernels)
string
required
URL-friendly identifier (slug) of the kernel, typically lowercase with hyphens (e.g., ‘my-analysis-notebook’)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_LIST_COMPETITION_FILESTool to list all data files available for a Kaggle competition. Use when you need to retrieve file names, sizes, and metadata for competition datasets before downloading.

Input Parameters

string
required
Competition name or URL slug (identifier). Find this in the competition’s URL: kaggle.com/competitions/{slug}

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_LIST_COMPETITIONSTool to list available Kaggle competitions with filters and pagination. Use when you need to discover competitions, search by keywords, or filter by category, group, and sorting options.

Input Parameters

integer
Page number for paginated results. Each page typically returns 20 competitions. Default: 1.
string ("general" | "entered" | "inClass")
Competition group filter options.
Search terms to filter competitions by keywords in title or description. Default: empty (no search filter).
string ("grouped" | "prize" | "earliestDeadline" | "latestDeadline" | "numberOfTeams" | "recentlyCreated")
Competition sorting options.
string ("all" | "featured" | "research" | "recruitment" | "gettingStarted" | "masters" | "playground")
Competition category filter options.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_LIST_DATASETSTool to list Kaggle datasets with filters and pagination. Use after authenticating with Kaggle API key.

Input Parameters

integer
Page number for paginated results. Default: 1. Increment by 1 on each subsequent call to paginate; stop when a call returns no data.
string
DEPRECATED: use max_size and min_size instead. Legacy size filter. Default behavior: all.
string
Filter datasets by a specific user or organization.
string
Display datasets by a particular group. Valid values: ‘public’ (all public datasets), ‘mine’ (user’s own datasets), ‘user’ (datasets by specific user when combined with ‘user’ parameter). Default: public.
string
Search terms to filter datasets. Default: empty.
string
Comma-separated list of tag IDs to filter by.
string
Filter datasets by license group. Valid values: ‘all’, ‘cc’, ‘gpl’, ‘odb’, ‘other’. Default: all.
string
Sort the results. Valid values: ‘hottest’, ‘votes’, ‘updated’, ‘active’. Default: hottest.
string
Filter datasets by file type. Valid values: ‘all’, ‘csv’, ‘sqlite’, ‘json’, ‘bigQuery’. Default: all.
integer
Maximum dataset size in bytes.
integer
Minimum dataset size in bytes.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_LIST_KERNEL_OUTPUT_FILESTool to list output files for a specific kernel run. Use when you need to retrieve paginated file listings by kernel owner and slug.

Input Parameters

integer
Number of items per page (default: 20, max: 200).
string
required
Kernel owner username.
string
Page token for results paging.
string
required
Kernel slug/name.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_LIST_KERNELSTool to list Kaggle kernels (notebooks and scripts) with filters and pagination. Use to discover kernels by search terms, user, language, type, competition, or dataset.

Input Parameters

integer
Page number for paginated results. Default: 1.
string
Filter kernels by a specific user or organization username.
string ("everyone" | "profile" | "upvoted")
Groups for filtering kernels.
string
Search terms to filter kernels by title, code, or author.
string ("hotness" | "commentCount" | "dateCreated" | "dateRun" | "scoreAscending" | "scoreDescending" | "viewCount" | "voteCount" | "relevance")
Sort options for kernel listings.
string
Filter kernels that use a specific dataset (format: owner/dataset-name).
string ("all" | "python" | "r" | "sqlite" | "julia")
Programming languages supported by Kaggle kernels.
integer
Number of kernels per page. Default: 20.
string ("all" | "script" | "notebook")
Types of Kaggle kernels.
string ("all" | "visualization" | "data")
Output types for Kaggle kernels.
string
Filter kernels associated with a specific competition (format: competition-slug).
string
Filter kernels that have forked the specified kernel (format: owner/kernel-name).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_LIST_MODEL_INSTANCE_VERSION_FILESTool to list files for a specific version of a model variation. Use when you need to retrieve files for a particular model framework instance version by owner, model, framework, variation, and version.

Input Parameters

string
required
Framework name (e.g., pyTorch, tensorFlow).
integer
Number of items per page (default: 20).
string
required
Model name/slug.
string
required
Model owner username.
string
Page token for results paging.
string
required
Variation name/slug (instance slug).
integer
required
Version number of the model variation.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_LIST_MODELSTool to list Kaggle models with optional filters for owner, sorting, search, and pagination. Use to discover available models on Kaggle’s platform.

Input Parameters

string
Filter to display models by a specific user or organization. Use the owner’s username or organization slug.
string
Search terms to filter models by title, owner, or other text fields. Leave empty to return all models.
string ("hotness" | "downloadCount" | "voteCount" | "notebookCount" | "publishTime" | "createTime" | "updateTime")
Enum for valid model list sort options.
integer
Number of models to return per page. Default: 20. Maximum: 100.
string
Page token for pagination. Use the ‘nextPageToken’ from a previous response to fetch the next page of results. Omit for the first page.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_PULL_KERNELPull a Kaggle kernel’s notebook or script source as downloadable content, optionally including kernel metadata JSON.

Input Parameters

string
Deprecated. Local download paths are no longer returned.
boolean
Deprecated. Local file caching is no longer used.
boolean
If true, include kernel-metadata.json file in the download. This file contains kernel configuration details like language, GPU settings, and dataset references.
string
required
Kernel owner username (e.g., ‘kami1976’). This is the username of the person or organization that owns the kernel.
string
required
Kernel name/slug (e.g., ‘stanford-rna-3d-enhanced-model’). This is the URL-friendly identifier for the kernel, typically lowercase with hyphens.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: KAGGLE_VIEW_COMPETITION_LEADERBOARDTool to view competition leaderboard information showing rankings and scores of participants. Use when you need to check competition standings, team scores, or analyze leaderboard positions.

Input Parameters

string
required
Competition name or URL slug (identifier). Find this in the competition’s URL: kaggle.com/competitions/{slug}

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not