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 61–90 of 840 actions
DATAROBOT_CREATE_DEPLOYMENTS_ACTUALS_DATA_EXPORTS
Tool to create a deployment actuals data export for a specified time period. Use when you need to export actuals data from a deployment to analyze model performance and accuracy.
Untrusted display-only summary
DATAROBOT_CREATE_DEPLOYMENTS_ACTUALS_FROM_DATASET
Tool to submit actuals values from AI Catalog dataset for deployment monitoring. Use when you need to upload actual outcomes for predictions to enable accuracy tracking and monitoring. The submission is asynchronous - poll the Location header URL to check completion status.
Untrusted display-only summary
DATAROBOT_CREATE_DEPLOYMENTS_ACTUALS_FROM_JSON
Submit actual values for predictions to a DataRobot deployment. Use this to track model accuracy and performance over time by providing ground truth values that can be compared against predictions.
Untrusted display-only summary
DATAROBOT_CREATE_DEPLOYMENTS_CUSTOM_METRICS
Create a deployment custom metric for monitoring deployment or model-specific metrics. Use for numeric metrics (average, gauge, sum) or categorical metrics to track custom KPIs beyond standard monitoring.
Untrusted display-only summary
DATAROBOT_CREATE_DEPLOYMENTS_CUSTOM_METRICS_BULK_UPLOAD
Bulk upload custom metric values to a DataRobot deployment. Use this to efficiently submit multiple timestamped custom metric values in a single request for model monitoring and observability.
Untrusted display-only summary
DATAROBOT_CREATE_DEPLOYMENTS_CUSTOM_METRICS_FROM_DATASET
Tool to upload custom metric values from a dataset to a deployment. Use when you need to populate custom metrics with data from an existing dataset. The operation is asynchronous and returns a location URL to check the import status.
Untrusted display-only summary
DATAROBOT_CREATE_DEPLOYMENTS_CUSTOM_METRICS_FROM_JSON
Tool to upload custom metric values from JSON for a DataRobot deployment. Use when you need to submit custom monitoring metrics (e.g., business KPIs, external performance measures) to track alongside model predictions. The operation is asynchronous - returns immediately with a location URL to poll for job status.
Untrusted display-only summary
DATAROBOT_CREATE_DEPLOYMENTS_MONITORING_BATCHES
Tool to create a monitoring batch for a DataRobot deployment. Use when you need to organize predictions into named batches for monitoring and tracking purposes. Monitoring batches help group related predictions for analysis and reporting.
Untrusted display-only summary
DATAROBOT_CREATE_DEPLOYMENTS_MONITORING_DATA_DELETIONS
Tool to delete deployment monitoring data for a specific model within a time period. Use when you need to remove historical monitoring data for a model in a deployment. Specify time ranges using top-of-the-hour RFC3339 datetime strings.
Untrusted display-only summary
DATAROBOT_CREATE_DEPLOYMENTS_PREDICTION_DATA_EXPORTS
Tool to create a prediction data export for a deployment. Use when you need to export prediction data for observability and data exploration.
Untrusted display-only summary
DATAROBOT_CREATE_DEPLOYMENTS_RETRAINING_POLICIES
Tool to create a deployment retraining policy in DataRobot. Use when you need to set up automated model retraining based on schedules, data drift, or accuracy decline triggers.
Untrusted display-only summary
DATAROBOT_CREATE_DEPLOYMENTS_TRAINING_DATA_EXPORTS
Tool to create a deployment training data export in DataRobot. Use when you need to export the training data used for a deployed model. The export is enqueued asynchronously and processes in the background. Poll the returned location URL to check export status and retrieve the data once ready.
Untrusted display-only summary
DATAROBOT_CREATE_ENTITY_NOTIFICATION_CHANNELS
Tool to create an entity notification channel in DataRobot. Use when you need to set up notifications for deployments or custom jobs.
Untrusted display-only summary
DATAROBOT_CREATE_ENTITY_NOTIFICATION_POLICIES
Tool to create an entity notification policy in DataRobot. Use when you need to set up automated notifications for specific events on deployments or custom jobs (e.g., health changes, model replacements, batch job completions). Requires a pre-existing notification channel; create one via the entity notification channe…
Untrusted display-only summary
DATAROBOT_CREATE_ENTITY_NOTIFICATION_POLICIES_FROM_TEMPLATE
Tool to create an entity notification policy from a template. Use when you need to set up automated notifications for events on deployments or custom jobs. The policy defines when notifications should be sent and through which channel (email, Slack, webhook, etc.).
Untrusted display-only summary
DATAROBOT_CREATE_ENTITY_NOTIFICATION_POLICY_TEMPLATE
Tool to create an entity notification policy template in DataRobot. Use when you need to set up notification rules for deployments or custom jobs. Templates allow you to define reusable notification policies that can be applied to multiple entities.
Untrusted display-only summary
DATAROBOT_CREATE_ENTITY_TAG
Tool to create a new entity tag in DataRobot. Use when you need to tag experiment containers for organization and categorization.
Untrusted display-only summary
DATAROBOT_CREATE_EXECUTION_ENVIRONMENTS_VERSIONS
Tool to create a new version for an existing DataRobot execution environment. Use when you need to add a new version to an execution environment by specifying a Docker image URI, Docker context, or Docker image file. The environment version build is asynchronous - the API returns immediately with a 202 status.
Untrusted display-only summary
DATAROBOT_CREATE_EXECUTION_ENVIRONMENTS_VERSIONS_DOWNLOAD
Tool to request an on-demand image build for an execution environment version. Use when you need to trigger a build for a specific environment version before downloading or deploying it.
Untrusted display-only summary
DATAROBOT_CREATE_EXT_DS_STANDARD_USER_DEF_FUNCTIONS
Tool to start a job that creates a standard user-defined function in an external data store. Use when you need to add rolling aggregation functions (median or most frequent) to a database for use in DataRobot feature engineering. Requires write permissions to the data store.
Untrusted display-only summary
DATAROBOT_CREATE_EXTERNAL_DATA_SOURCES
Tool to create a new external data source in DataRobot. Use when you need to create a connection to an external database or filesystem. Requires a valid dataStoreId from an existing data store connection.
Untrusted display-only summary
DATAROBOT_CREATE_EXTERNAL_DATA_STORES
Tool to create a new external data store in DataRobot. Use when establishing a connection to external databases or data systems. The created data store ID can then be used with CREATE_EXTERNAL_DATA_SOURCES to define specific tables or queries.
Untrusted display-only summary
DATAROBOT_CREATE_EXTERNAL_DATA_STORES_COLUMNS
Tool to retrieve column metadata from an external data store. Use when you need to discover the schema and data types of tables in an external database connection. Requires a valid dataStoreId and authentication credentials.
Untrusted display-only summary
DATAROBOT_CREATE_EXTERNAL_DATA_STORES_COLUMNS_INFO
Tool to retrieve column metadata for a table in an external data store. Use when you need to inspect the schema and structure of a database table. This operation is only supported for JDBC data stores.
Untrusted display-only summary
DATAROBOT_CREATE_EXTERNAL_DATA_STORES_SCHEMAS
Tool to retrieve data store schemas. Use when you need to list available schemas and catalogs from an external data store.
Untrusted display-only summary
DATAROBOT_CREATE_EXTERNAL_DATA_STORES_TABLES
Tool to retrieve database tables and views from a DataRobot external data store. Use when you need to browse available tables before creating a dataset from an external data source.
Untrusted display-only summary
DATAROBOT_CREATE_EXTERNAL_O_AUTH_PROVIDERS
Create an external OAuth provider configuration in DataRobot for integrating with external services. Use this to configure OAuth authentication for services like GitHub, GitLab, Bitbucket, Google, Box, Microsoft, Jira, or Confluence. The provider enables secure authentication flows for accessing external resources fro…
Untrusted display-only summary
DATAROBOT_CREATE_FILES
Tool to create an empty files catalog item in DataRobot. Use when you need to create a placeholder catalog entry before uploading files to it. After creating the empty catalog item, use CREATE_FILES_FROM_FILE or CREATE_FILES_FROM_URL to populate it with actual files.
Untrusted display-only summary
DATAROBOT_CREATE_FILES_COPY_BATCH
Tool to copy multiple files or folders in a batch operation within DataRobot's data registry. Use when you need to copy multiple files at once, either within the same catalog item or to a different catalog item.
Untrusted display-only summary
DATAROBOT_CREATE_FILES_DOWNLOADS
Tool to generate a temporary download URL for a DataRobot catalog file. Use when you need to download data from a catalog item. The download URL is valid for a limited time (default 60 seconds, maximum 5 minutes).
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.