---
title: "DataRobot integration for LuumenAI"
url: "https://www.luumen.ai/integrations/datarobot/"
entity: SoftwareIntegration
category: "AI & automation"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# DataRobot integration for LuumenAI

Check DataRobot projects and deployments, then make the change you approve

## What LuumenAI can do with DataRobot

LuumenAI connects to DataRobot with an API token and exposes 836 tools (476 read-only · 277 write · 83 destructive). Reads answer immediately; writes are shown as a plan and require approval by default, configurable per tool by an administrator.

## Key facts

- Authentication: API token
- Tools available: 836 tools (476 read-only · 277 write · 83 destructive)
- Plan: available on all plans
- Category: AI & automation

## About DataRobot with LuumenAI

Connect DataRobot and Luumen can answer questions about your projects, deployments, and data stores without you opening the UI. Ask what a project is doing, pull training or actuals exports, inspect external table metadata. When something needs to change — archiving a model package, building a scoring code package, canceling a stuck job — Luumen shows the plan first and waits for your approval. Authentication is by API key.

## Example tools

Read-only (476 in total):

- `DATAROBOT_CHECK_PROJECT_STATUS` — Check the status of a DataRobot project.
- `DATAROBOT_CREATE_CODE_SNIPPETS` — Generate code snippets for DataRobot models, predictions, or workloads.
- `DATAROBOT_CREATE_CODE_SNIPPETS_DOWNLOAD` — Download code snippets for DataRobot deployments, models, or workloads.
- `DATAROBOT_CREATE_DATA_SLICES_SLICE_SIZES` — Compute the number of rows available after applying a data slice to a dataset subset.
- `DATAROBOT_CREATE_DEPLOYMENTS_ACTUALS_DATA_EXPORTS` — Create a deployment actuals data export for a specified time period.
- `DATAROBOT_CREATE_DEPLOYMENTS_TRAINING_DATA_EXPORTS` — Create a deployment training data export in DataRobot.
- `DATAROBOT_CREATE_EXTERNAL_DATA_STORES_COLUMNS` — Retrieve column metadata from an external data store.
- `DATAROBOT_CREATE_EXTERNAL_DATA_STORES_COLUMNS_INFO` — Retrieve column metadata for a table in an external data store.

Write and destructive (360 in total, approval required by default):

- `DATAROBOT_ADD_USERS_TO_GROUP` — Add one or more users to a DataRobot user group by groupId.
- `DATAROBOT_ADD_USER_TO_ORGANIZATION` — Add a user to an existing organization.
- `DATAROBOT_ANALYZE_DATASET_DEFINITION` — Analyze a dataset definition by ID.
- `DATAROBOT_ARCHIVE_MODEL_PACKAGE` — Archive a DataRobot model package.
- `DATAROBOT_BUILD_SCORING_CODE_JAVA_PACKAGE` — Initiates an asynchronous build of a Java JAR package containing DataRobot Scoring Code for a deployment.
- `DATAROBOT_CANCEL_NOTEBOOK_JOB` — Cancel a running or pending notebook job execution.
- `DATAROBOT_CANCEL_PROJECT_JOB` — Cancel a pending job for a project.
- `DATAROBOT_CLONE_APPLICATION_TEMPLATE` — Clone an application template into a codespace.

## Frequently asked questions

### How does LuumenAI connect to DataRobot?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

### Can LuumenAI change things in DataRobot on its own?

Read actions answer immediately. Anything that writes is shown as a plan and requires approval by default, including the 83 actions classified as destructive. Administrators configure that per tool.

### Is there an audit trail?

Every call to DataRobot — read or write, approved or declined — is recorded with the actor, the input, and the result.

Full page: https://www.luumen.ai/integrations/datarobot/