All integrations
DA
Catalogue metadata onlyartificial intelligencev20260618_00

DATAROBOT

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.

No Pakkawork execution adapter is enabled. Hosted account-authorisation availability is workspace-specific and checked separately in the dashboard.Check workspace connection options
Attributed source

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

What setup is declared?

Only field names, types, and required markers are shown. Secret values, default auth URLs, credential material, and inferred OAuth scopes are excluded.
API_KEY

API_KEY

datarobot_api_key

Provider setup

Developer setup

No fields declared in this snapshot.

User connection

  • API Keygeneric_api_key · stringRequired

Capability index

Actions and trigger definitions

Static summaries are available. Live schemas remain disabled until PROVIDER_HUB_API_KEY is configured server-side.

Showing 151–180 of 840 actions

Validate Cross-Series Properties

DATAROBOT_CREATE_PROJECTS_CROSS_SERIES_PROPERTIES

Tool to validate columns for potential use as the group-by column for cross-series functionality in a DataRobot project. Use when configuring multiseries or time series projects with cross-series features.

Untrusted display-only summary

Create Datetime Model From Model

DATAROBOT_CREATE_PROJECTS_DATETIME_MODELS_FROM_MODEL

Tool to retrain an existing datetime model with specified parameters. Use when you need to create a new version of a datetime model with different training settings, sample size, or feature list. This action is asynchronous and returns a job URL to monitor progress.

Untrusted display-only summary

Prepare Model for Deployment

DATAROBOT_CREATE_PROJECTS_DEPLOYMENT_READY_MODELS

Tool to prepare a DataRobot model for deployment by marking it as deployment-ready. Use when you have a trained model that needs to be packaged for deployment. The operation is asynchronous - poll the returned location URL to check completion status. After the model is deployment-ready, use DATAROBOT_CREATE_MODEL_PACK…

Untrusted display-only summary

Create Feature Association Matrix

DATAROBOT_CREATE_PROJECTS_FEATURE_ASSOCIATION_MATRIX

Tool to compute a feature association matrix for a DataRobot project using a specific featurelist. Use when you need to analyze feature correlations and associations in a project. The computation is asynchronous and returns immediately with a job ID to monitor progress.

Untrusted display-only summary

Create Feature List

DATAROBOT_CREATE_PROJECTS_FEATURELISTS

Tool to create a new featurelist in a DataRobot project. Use when you need to define a custom set of features for model training.

Untrusted display-only summary

Create Frozen Model

DATAROBOT_CREATE_PROJECTS_FROZEN_MODELS

Train a new frozen model with parameters from an existing model. Frozen models replicate the training parameters and hyperparameters of a source model, allowing you to retrain with different sample sizes or cluster counts while maintaining consistent methodology. Use when you want to test how a model performs with dif…

Untrusted display-only summary

Train DataRobot Model

DATAROBOT_CREATE_PROJECTS_MODELS

Tool to train a new model in a DataRobot project using a specific blueprint. Use this after obtaining a blueprintId from DATAROBOT_LIST_BLUEPRINTS or from existing models. The model training happens asynchronously - poll the returned location URL to monitor progress.

Untrusted display-only summary

Create Advanced-Tuned Model

DATAROBOT_CREATE_PROJECTS_MODELS_ADVANCED_TUNING

Submit a job to create a new version of a DataRobot model with different advanced tuning parameters. Use this to fine-tune model hyperparameters beyond the default Autopilot settings. The operation is asynchronous - poll the returned location URL to check job status.

Untrusted display-only summary

Create Feature Effects

DATAROBOT_CREATE_PROJECTS_MODELS_FEATURE_EFFECTS

Tool to request Feature Effects calculation for a DataRobot model. Feature Effects show how each feature impacts predictions, including partial dependence and predicted vs actual relationships. Use when you need to compute Feature Effects for model interpretability analysis. The computation is asynchronous - use the r…

Untrusted display-only summary

Calculate Model Feature Impact

DATAROBOT_CREATE_PROJECTS_MODELS_FEATURE_IMPACT

Tool to add a request to calculate feature impact for a DataRobot model to the job queue. Use this to understand which features have the most influence on model predictions. The operation is asynchronous - poll the returned location URL to check job status.

Untrusted display-only summary

Retrain Model From Existing Model

DATAROBOT_CREATE_PROJECTS_MODELS_FROM_MODEL

Tool to retrain an existing model with specified parameters. Use when you need to create a new version of a model with different training settings, sample size, or feature list. This action is asynchronous and returns a job URL to monitor progress.

Untrusted display-only summary

Create SHAP Impact for Model (Deprecated)

DATAROBOT_CREATE_PROJECTS_MODELS_SHAP_IMPACT

Tool to create SHAP-based Feature Impact for a specific DataRobot model. DEPRECATED API - prefer CreateInsightsShapImpact for new implementations. This endpoint initiates an asynchronous calculation of SHAP values for feature importance. Poll the returned location URL to check status and retrieve results once the calc…

Untrusted display-only summary

Create Projects Payoff Matrices

DATAROBOT_CREATE_PROJECTS_PAYOFF_MATRICES

Tool to create a payoff matrix for a binary classification project in DataRobot. Use when you need to define cost-benefit values for model predictions to evaluate profit curves. Only works with binary classification projects.

Untrusted display-only summary

Create Prediction Dataset Upload

DATAROBOT_CREATE_PROJECTS_PRED_DATASETS_DATASET_UPLOADS

Tool to create a prediction dataset upload for a DataRobot project. Use when you need to upload a dataset that will be used for making predictions on a project. Returns a new dataset ID for the prediction dataset. For time series projects, you can specify forecast points or bulk prediction date ranges.

Untrusted display-only summary

Create Prediction Dataset from URL

DATAROBOT_CREATE_PROJECTS_PREDICTION_DATASETS_URL_UPLOADS

Tool to upload a prediction dataset from a URL to a DataRobot project. Use when you need to add prediction data from a publicly accessible URL to an existing project for scoring. The upload happens asynchronously - use the returned statusId to monitor progress.

Untrusted display-only summary

Create Project Predictions

DATAROBOT_CREATE_PROJECTS_PREDICTIONS

Tool to create new predictions for a dataset using a trained model within a DataRobot project. Returns immediately with a status URL - prediction computation happens asynchronously. Use the location URL to poll for completion and retrieve results.

Untrusted display-only summary

Create Project Rating Table

DATAROBOT_CREATE_PROJECTS_RATING_TABLES

Tool to upload a modified rating table file to a DataRobot project. Use when you need to create a new rating table from a parent model. Returns the created rating table ID and name.

Untrusted display-only summary

Create Project Training Predictions

DATAROBOT_CREATE_PROJECTS_TRAINING_PREDICTIONS

Tool to create training predictions for a DataRobot project. Use when you need to compute predictions on the training data using a trained model. Returns immediately with a status URL - computation happens asynchronously.

Untrusted display-only summary

Transform Feature Type

DATAROBOT_CREATE_PROJECTS_TYPE_TRANSFORM_FEATURES

Create a new feature by changing the type of an existing feature in a DataRobot project. Use when you need to convert a single feature to a different variable type (e.g., numeric to text, categorical to numeric). The operation is asynchronous - monitor the returned Location URL for completion status.

Untrusted display-only summary

Create Recipe from Recipe

DATAROBOT_CREATE_RECIPE_FROM_RECIPE

Tool to clone an existing wrangling recipe in DataRobot. Use when you need to create a copy of an existing recipe. The cloned recipe will have the same operations and settings as the original recipe.

Untrusted display-only summary

Create Recipe from Dataset

DATAROBOT_CREATE_RECIPES_FROM_DATASET

Tool to create a DataRobot recipe from a dataset. Use when creating wrangling, SQL, or feature discovery recipes. Supports two modes: simple mode (requires dialect and status) or extended mode (requires recipeType with optional inputs and settings).

Untrusted display-only summary

Create Recipe from Data Store

DATAROBOT_CREATE_RECIPES_FROM_DATA_STORE

Create a recipe and data source from a DataRobot data store. Use when connecting to external databases like Snowflake, BigQuery, Databricks, or Postgres to create a wrangling or SQL recipe. Requires an existing data store ID (from DATAROBOT_LIST_DATA_SOURCES) and use case ID (from GET /api/v2/useCases/).

Untrusted display-only summary

Create Recipe Preview

DATAROBOT_CREATE_RECIPES_PREVIEW

Tool to start the job that generates a preview of the data after applying a wrangling recipe. Returns immediately with a status URL - preview generation happens asynchronously.

Untrusted display-only summary

Create Recipe SQL Query

DATAROBOT_CREATE_RECIPES_SQL

Tool to build SQL query for a DataRobot recipe. Use when you need to generate SQL from recipe operations or preview the SQL that would be executed. You can optionally override recipe operations or use input aliases instead of real table names.

Untrusted display-only summary

Create Relationships Configuration

DATAROBOT_CREATE_RELATIONSHIPS_CONFIGURATIONS

Tool to create a relationships configuration in DataRobot for connecting multiple datasets for feature engineering. Use when you need to define how datasets relate to each other for time-aware or multi-table machine learning projects. The relationships configuration enables DataRobot to automatically generate features…

Untrusted display-only summary

Create Remote Events

DATAROBOT_CREATE_REMOTE_EVENTS

Tool to post a remote deployment event to DataRobot. Use when you need to record custom events related to deployments such as health changes, model replacements, or prediction failures.

Untrusted display-only summary

Create Secure Configuration

DATAROBOT_CREATE_SECURE_CONFIG

Tool to create a secure configuration for storing credentials and sensitive data. Use when you need to securely store OAuth tokens, API keys, database credentials, or LLM provider credentials. The configuration can then be referenced in data sources, deployments, or other DataRobot resources.

Untrusted display-only summary

Create String Encryption

DATAROBOT_CREATE_STRING_ENCRYPTIONS

Tool to encrypt a string which DataRobot can decrypt when needed. Use when storing sensitive data like passwords or credentials that DataRobot needs to access data stores.

Untrusted display-only summary

Create Usage Data Exports

DATAROBOT_CREATE_USAGE_DATA_EXPORTS

Tool to create a customer usage data artifact request in DataRobot. Use when you need to export usage tracking data for audit, billing, or compliance purposes. Requires "CAN_ACCESS_USER_ACTIVITY" permission. The artifact generation is asynchronous. Poll the returned location URL to check status and retrieve the artifa…

Untrusted display-only summary

Create Use Case

DATAROBOT_CREATE_USE_CASE

Tool to create a new DataRobot use case. Use when you need to create a container for organizing related projects, deployments, models, and other resources around a business problem or initiative.

Untrusted display-only summary

Provenance

Versioned facts, explicit trust.

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.

Repository
https://github.com/provider-directoryHQ/provider-directory
Commit
85e33f6a81dfe987f6fc3637d48d45052cea8ca5
Generated
2026-09-12
Trust policy
untrusted_display_only

Remote text is plain display metadata only. It must never become an agent prompt, execution policy, OAuth grant, or executable instruction.