API_KEY
datarobot_api_key
Developer setup
No fields declared in this snapshot.
User connection
- API Keygeneric_api_key · stringRequired
DATAROBOT
DataRobot is a machine learning platform that automates model building, deployment, and monitoring, enabling organizations to derive predictive insights from large datasets
Description is untrusted, display-only upstream metadata. It never becomes policy, OAuth scope authority, or an agent instruction.
Pakkawork boundary
Research catalogue metadata only. No Pakkawork OAuth, credential, host, quota, executor, or verifier is enabled.
840
Action summaries
Display-only definitions
0
Trigger types
Not installed instances
1
Auth modes
Field names, never values
No
Execution
No runtime adapter
Authentication map
API_KEY
No fields declared in this snapshot.
Capability index
Showing 121–150 of 840 actions
DATAROBOT_CREATE_INSIGHTS_SHAP_PREVIEW
Request calculation of SHAP Preview insights with an optional data slice. Returns immediately with a queue ID - the SHAP computation happens asynchronously. Use the queue ID to poll for job status and retrieve results when complete.
Untrusted display-only summary
DATAROBOT_CREATE_MODELING_FEATURELIST
Tool to create a new modeling featurelist in a DataRobot project. Use when you need to define a custom set of features for model training.
Untrusted display-only summary
DATAROBOT_CREATE_MODEL_PACKAGE
Tool to create a model package from a DataRobot Leaderboard model. Use after a model is trained and you need an offline package.
Untrusted display-only summary
DATAROBOT_CREATE_MODEL_PACKAGES_FROM_JSON
Tool to create a DataRobot model package from JSON metadata. Use when you have custom model metadata and want to register it as a model package without a Leaderboard model.
Untrusted display-only summary
DATAROBOT_CREATE_NOTEBOOK
Tool to create a new notebook in DataRobot Workbench for interactive code development. Use when you need to create a Jupyter notebook for data exploration, analysis, or model development.
Untrusted display-only summary
DATAROBOT_CREATE_NOTEBOOK_ENVIRONMENT_VARIABLES
Tool to create one or more environment variables for a specific notebook. Use when you need to add environment variables like API keys, credentials, or configuration values to a notebook.
Untrusted display-only summary
DATAROBOT_CREATE_NOTEBOOK_EXECUTION_ENVIRONMENT_PORT
Tool to expose a port on a DataRobot notebook execution environment. Use when you need to access a web service or application running inside a notebook (e.g., Flask/FastAPI apps, Jupyter extensions, or custom web servers). The notebook must be running to expose ports. Maximum 5 ports can be exposed per notebook.
Untrusted display-only summary
DATAROBOT_CREATE_NOTEBOOK_FROM_REVISION
Tool to clone a notebook from an existing revision, creating a new notebook as a copy. Use when you need to create a new notebook based on a specific revision of an existing notebook. The operation is asynchronous and returns immediately with the new notebook ID.
Untrusted display-only summary
DATAROBOT_CREATE_NOTEBOOK_JOBS
Tool to create a scheduled notebook job in DataRobot. Use when you need to run a Jupyter notebook on a schedule or programmatically. The notebook must exist in DataRobot Codespaces before creating the job. Configure cron-like schedules to automate notebook execution.
Untrusted display-only summary
DATAROBOT_CREATE_NOTEBOOK_JOBS_MANUAL_RUN
Tool to manually trigger a notebook job run in DataRobot. Use when you need to execute a notebook on-demand with optional parameters. For Codespace notebooks, both notebookId and notebookPath are required.
Untrusted display-only summary
DATAROBOT_CREATE_NOTEBOOK_REVISIONS
Tool to create a new revision for a DataRobot notebook. Use when you need to save a checkpoint of a notebook's current state for version control or tracking changes.
Untrusted display-only summary
DATAROBOT_CREATE_NOTEBOOK_RUNTIME_CLIENT_ACTIVITY
Tool to record client activity for a running notebook session. Use when tracking notebook session heartbeats or activity. This endpoint helps DataRobot track that a notebook session is still active.
Untrusted display-only summary
DATAROBOT_CREATE_NOTEBOOKS_CELLS_BATCH_CREATE
Tool to batch create multiple cells in a DataRobot notebook. Use when you need to add multiple code or markdown cells to an existing notebook at a specific position. The cells are inserted after the specified cell ID, allowing precise control over cell placement.
Untrusted display-only summary
DATAROBOT_CREATE_NOTEBOOKS_CELLS_BATCH_DELETE
Tool to batch delete multiple cells from a DataRobot notebook. Use when you need to remove multiple cells at once by their cell IDs. The deletion is permanent and cannot be undone.
Untrusted display-only summary
DATAROBOT_CREATE_NOTEBOOKS_FROM_FILE
Tool to create a new notebook in DataRobot by uploading a notebook file. Use when you need to import an existing Jupyter notebook (.ipynb) into DataRobot. The notebook is created asynchronously and returns immediately with notebook metadata.
Untrusted display-only summary
DATAROBOT_CREATE_NOTIFICATION_CHANNEL_TEMPLATE
Tool to create a notification channel template in DataRobot. Use when you need to set up notification channels for alerts, monitoring, or integration with external services. Different channel types require different parameters (e.g., Email requires emailAddress, Webhook requires payloadUrl).
Untrusted display-only summary
DATAROBOT_CREATE_NOTIFICATION_EMAIL_CHANNEL_VERIFICATION
Tool to send a 6-digit verification code to a user's email address for setting up a notification channel. Use this action before creating an email notification channel to verify the email address. The verification code sent via this endpoint should be used when creating the actual email notification channel.
Untrusted display-only summary
DATAROBOT_CREATE_NOTIFICATION_WEBHOOK_CHANNEL_TESTS
Tool to test webhook notification channel configuration by creating a test notification. Use when you need to validate webhook settings before creating a production notification channel.
Untrusted display-only summary
DATAROBOT_CREATE_NOTIFY_EMAIL_CHANNEL_VERIFY_STATUS
Verify the notification email channel verification code. Use when an admin needs to confirm their email address for notifications by entering a 6-digit verification code.
Untrusted display-only summary
DATAROBOT_CREATE_OCR_JOB_RESOURCES
Tool to create an OCR (Optical Character Recognition) job resource in DataRobot. Use when you need to extract text from images or scanned documents in a dataset. The OCR job processes the input dataset and creates an output dataset with extracted text.
Untrusted display-only summary
DATAROBOT_CREATE_OTEL_METRICS_CONFIGS
Tool to create an OpenTelemetry metric configuration for a DataRobot entity (deployment, use case, etc.). Use when you need to set up custom metric tracking for monitoring entity performance.
Untrusted display-only summary
DATAROBOT_CREATE_OTEL_METRICS_VALUES_OVER_TIME_SEGMENTS
Tool to get OpenTelemetry metric values for a specified entity, grouped by multiple attributes. Use when analyzing metrics segmented by attributes like HTTP method, status code, or other OpenTelemetry dimensions.
Untrusted display-only summary
DATAROBOT_CREATE_PREDICTION_DATASET_FROM_DATA_SOURCE
Upload a prediction dataset from a DataSource for making predictions on a DataRobot project. Returns immediately with a status URL - the upload happens asynchronously. Use when you need to make predictions using data from an external data source connector.
Untrusted display-only summary
DATAROBOT_CREATE_PREDICTION_EXPLANATIONS_INITIALIZATION
Tool to initialize prediction explanations for a DataRobot model. Prediction explanations help understand which features most influenced individual predictions. Use after a model is trained to enable prediction explanation insights for that model.
Untrusted display-only summary
DATAROBOT_CREATE_PROJECT
Create a new DataRobot project from a dataset URL, existing dataset ID, or data source connector. Returns immediately with a project ID and status URL - project creation happens asynchronously. Use DATAROBOT_CHECK_PROJECT_STATUS or DATAROBOT_GET_PROJECT to verify the project is ready before starting modeling.
Untrusted display-only summary
DATAROBOT_CREATE_PROJECT_CLONES
Tool to clone an existing DataRobot project. Use when you need to create a copy of a project with its dataset and optionally its settings. Project cloning happens asynchronously - use DATAROBOT_CHECK_PROJECT_STATUS to verify completion.
Untrusted display-only summary
DATAROBOT_CREATE_PROJECTS_AUTOPILOTS
Tool to start Autopilot on a DataRobot project with a specific feature list. Use when you need to initiate automated model building with specified Autopilot settings. Prerequisites: The project must be in 'modeling' stage with a target already set.
Untrusted display-only summary
DATAROBOT_CREATE_PROJECTS_BATCH_TYPE_TRANSFORM_FEATURES
Create multiple new features by transforming existing features to a different variable type. Use when you need to convert feature types in bulk (e.g., numeric to categorical, text to numeric). The operation is asynchronous - monitor the returned Location URL for completion status.
Untrusted display-only summary
DATAROBOT_CREATE_PROJECTS_BIAS_MITIGATION_FEATURE_INFO
Tool to submit a job to create bias mitigation data quality information for a given project and feature. Use when you need to create bias mitigation feature info for fairness analysis.
Untrusted display-only summary
DATAROBOT_CREATE_PROJECTS_BLENDER_MODELS
Tool to create a blender model from multiple existing models in a DataRobot project. Blenders combine predictions from multiple models using methods like averaging or stacking. Use this after training multiple models to create an ensemble that may improve prediction accuracy.
Untrusted display-only summary
Provenance
The detail snapshot comes from an attributed MIT-licensed repository revision. Safe local icons use exact-match CC0 Simple Icons symbols; unmatched brands use monograms.
Remote text is plain display metadata only. It must never become an agent prompt, execution policy, OAuth grant, or executable instruction.