DataRobot

Tool to add one or more users to a DataRobot user group by groupId. Use when you have a valid groupId and want to add existing usernames. Limit 100 users per request.

Tool to add a user to an existing organization. Use when you have an organizationId and wish to add or create a user within it.

Tool to analyze a dataset definition by ID. Use when you need to trigger an analysis job that retrieves dataset metadata, schema, and statistics.

Tool to archive a DataRobot model package. Use when you need to archive a model package that is no longer actively used.

Initiates an asynchronous build of a Java JAR package containing DataRobot Scoring Code for a deployment. The JAR can be executed locally for predictions or used as a library in Java applications. Use after confirming the deployment is active and supports scoring code. Poll the returned statusId or location URL to track build progress.

Tool to cancel a running or pending notebook job execution. Use when you need to stop a notebook job that is currently executing or queued. The cancellation is immediate and cannot be undone.

Tool to cancel a pending job for a project. Use when you need to stop a queued or running job after confirming its ID.

Tool to check the status of a DataRobot project. Use after creating or loading a project to monitor its stage and Autopilot completion.

Tool to clone an application template into a codespace. Use when you need to create a new codespace from an existing template.

Tool to create a duplicate files collection in DataRobot. Use when you need to clone an existing files catalog item, optionally excluding specific files. The cloning operation is asynchronous - poll the returned location URL to check status.

Tool to copy a file or folder within the same DataRobot catalog item. Use when you need to duplicate files or folders in the data registry with configurable overwrite strategies.

Create a custom Access Role for an organization. Use to define tailored permission sets controlling user access to DataRobot entities (projects, deployments, datasets, etc.). Requires an organization ID which can be obtained from the account info endpoint.

Tool to create and start a new notebook codespace in DataRobot. Use when you need to set up an interactive Jupyter notebook environment within a use case. Note: DataRobot limits concurrent notebooks to 4 running in parallel. If the limit is reached, stop or delete an existing notebook before creating a new one.

Tool to request generation of automated compliance documents in DataRobot. Use when you need to generate documentation for projects, models, or deployments. The document generation is asynchronous. Poll the returned location URL to check status and retrieve the document once generation completes.

Tool to create a DataRobot Batch Monitoring job for tracking model performance and data drift on batch predictions. Use when you need to monitor predictions at scale. The job is created asynchronously and returns immediately with a job ID.

Tool to create a Batch Monitoring job definition for tracking deployment performance and data drift. Use when you need to set up scheduled or manual monitoring jobs for a DataRobot deployment.

Tool to create a Batch Prediction job definition. Use when you need to manually or scheduled scoring on large datasets.

Tool to create a new batch predictions job in DataRobot. Use when you need to score large datasets using a deployment, model, or model package. The job processes predictions asynchronously.

Tool to create a new Batch Prediction job based on an existing job's configuration. Use when you need to re-run predictions with the same settings.

Tool to launch a Batch Prediction job from a job definition. Use when you need to execute a previously created batch prediction job definition for scoring.

Tool to create a DataRobot calendar by uploading a CSV or XLSX file containing date events. Use when you need to define custom calendars for time-series modeling with specific event dates. The operation is asynchronous - poll the returned location URL to check completion status.

Initialize generation of preloaded calendars from a country code. Creates calendars with national holidays for the specified country and date range. Calendar generation is asynchronous - poll the returned location URL to check completion status.

Tool to create a calendar from a dataset in DataRobot. Use when preparing time-series projects that require custom calendar definitions. Calendar creation is asynchronous - use the returned statusId to monitor progress.

Create a Change Request for a DataRobot deployment to enable governance workflows. Use when you need to request approval for deployment changes such as changing importance, replacing models, updating status, or deleting deployments. Change requests require approval from authorized reviewers before changes can be applied.

Tool to generate code snippets for DataRobot models, predictions, or workloads. Use when you need sample code to interact with DataRobot models, make predictions, or process workloads in various programming languages.

Tool to download code snippets for DataRobot deployments, models, or workloads. Use when you need sample code to make predictions, interact with models, or work with workloads. Generates code in Python, cURL, PowerShell, or Qlik based on your deployment/model configuration.

Tool to create a comment on a DataRobot entity (deployment, use case, model, catalog, etc.). Use when you need to add notes, feedback, or documentation to DataRobot objects.

Tool to create a new compliance documentation template in DataRobot. Use when you need to define a reusable structure for model compliance documentation. Templates can include DataRobot-generated content, user-provided text, custom sections, and table of contents. Sections can be nested up to 5 levels deep with a maximum of 500 total sections.

Store a new set of credentials in DataRobot for use with data sources and connections. Supports multiple credential types including basic auth, OAuth, cloud provider credentials (AWS, GCP, Azure), and database-specific authentication. Use when you need to securely store credentials for connecting to external data sources or services.

Tool to create a custom application source in DataRobot. Use when you need to create a new source for custom applications.

Create a new custom application source version in DataRobot. Use when you need to create a new version of an existing custom application source with optional file uploads, environment configuration, or based on a previous version.

Tool to create a custom application source from a custom template. Use when you need to instantiate a new application source based on an existing custom template.

Tool to create a new DataRobot custom job. Use when you need to define a custom execution task that runs arbitrary Python code in DataRobot's managed environment. Only the 'name' field is required; DataRobot applies sensible defaults for other fields.

Tool to permanently delete a custom job. Use when you need to permanently remove a soft-deleted custom job and all its components. The custom job must be soft-deleted first before permanent deletion.

Tool to create a hosted custom metric template for a DataRobot custom job. Use when defining how custom metrics should be collected and aggregated for observability. The template must specify whether metrics are model-specific, the aggregation type, and for numeric metrics, directionality and units.

Tool to create a new DataRobot custom model for training or inference. Use when you need to register a custom model in DataRobot. For inference models, targetType and targetName are typically required (e.g., targetType='Regression' requires targetName).

Tool to request logs from a deployed custom model. Use when troubleshooting failed prediction requests or debugging custom model behavior. Returns a status ID for polling - logs are generated asynchronously.

Tool to clone an existing custom model in DataRobot. Use when you need to create a copy of a custom model for reuse or experimentation.

Tool to create a new version for an existing DataRobot custom model. Use when you need to update a custom model with new code files, environment changes, or configuration updates. Creates either a major or minor version based on the isMajorUpdate parameter.

Tool to start data disparity insight calculations for a DataRobot model. Use when you need to analyze data disparity between two classes for a specific feature. The calculation is asynchronous; poll the returned location URL to check job status and retrieve results.

Create a Data Engine workspace state by executing a SQL query against DataRobot datasets. Use when you need to transform, join, or prepare data before modeling. The workspace state captures the query definition and can be used to generate new datasets or feed into projects.

Create a dataset definition in DataRobot to define how to access and use a dataset from the AI Catalog. Use when you need to establish a reusable definition for a dataset that can be referenced in projects and deployments.

Tool to create a chunk definition for a dataset definition in DataRobot. Use when you need to define how to partition a dataset into chunks for distributed processing or validation strategies.

Tool to create a custom feature list within a dataset. Use when you need to define a specific subset of features for analysis or modeling.

Tool to create a DataRobot dataset by uploading a file (CSV, Excel, etc.). Use when you need to upload data files to DataRobot's global catalog for modeling or prediction. Dataset creation is asynchronous - poll the statusId to monitor completion.

Tool to create a feature transform on a DataRobot dataset. Use when you need to transform an existing feature into a new feature with a different type or extract date components. Feature creation is asynchronous - poll the returned location URL to check status.

Tool to create a dataset from an external data source connector (database, S3, etc.). Use when you need to import data from a configured data source into DataRobot. The dataset creation is asynchronous - poll the returned location URL to check completion status.

Tool to create a dataset from a DataRobot wrangling recipe. Use when you need to materialize a recipe into a reusable dataset. Creation is asynchronous - poll the location URL to check completion status.

Tool to create a DataRobot dataset from a publicly accessible URL. Use when you need to import data from HTTP/HTTPS URLs into DataRobot's data catalog. Returns immediately with catalog and status IDs - dataset ingestion happens asynchronously.

Tool to schedule a dataset refresh job in DataRobot. Use when you need to automate periodic data updates for a dataset. The schedule must be at least daily (hourly schedules are not supported).

Tool to create dataset relationships in DataRobot by linking features between two datasets. Use when you need to enable advanced feature engineering across multiple datasets for modeling.

Tool to create a new dataset version from the latest version of its data source. Use when you need to refresh a dataset with updated data from its original source. The dataset version creation is asynchronous - poll the returned location URL to check completion status.

Tool to create a new version for an existing DataRobot dataset from a publicly accessible URL. Use when you need to update an existing dataset with new data from HTTP/HTTPS URLs. Returns immediately with status ID - version creation happens asynchronously.

Tool to create a new dataset version from a specific previous version of its data source. Use when you need to refresh a dataset based on a particular historical version. The dataset version creation is asynchronous - poll the returned location URL to check completion status.

Tool to create a new version of an existing DataRobot dataset by uploading a file (CSV, Excel, etc.). Use when you need to update an existing dataset with new data. Dataset version creation is asynchronous - poll the statusId to monitor completion.

Create a new data slice in a DataRobot project to define a subset of data based on feature filters. Use when you need to analyze or model specific segments of your data (e.g., high-value customers, specific regions). Supports up to 3 filters with operators: eq, in, <, >, between, notBetween.

Tool to compute the number of rows available after applying a data slice to a dataset subset. Use when validating data slice filters or checking how many rows will be included in analysis for a specific data partition. Returns slice size and validation messages. Status 202 indicates successful validation.

Tool to create a data stage in DataRobot. Use when you need to create a new data stage with a specified filename for data staging operations.

Create a DataRobot deployment from a model package to enable real-time or batch predictions. Prerequisites: 1. First obtain a modelPackageId using LIST_MODEL_PACKAGES or CREATE_MODEL_PACKAGE 2. Optionally get predictionEnvironmentId using LIST_PREDICTION_ENVIRONMENTS 3. For managed SaaS, get defaultPredictionServerId using LIST_PREDICTION_SERVERS The deployment is created asynchronously. Poll the returned location URL to check readiness status.

Tool to create a deployment custom metric from an existing custom job in DataRobot. Use when you need to track custom business or operational metrics for a deployment. The custom job must have an associated hosted custom metric template.