.DkNUKaKx_ZLAT4m.webp?dpl=dpl_ARtVL4739pNJnxC8yxqCNToe4mN7){kind=small}
Connectors / AI · HTTP Connector
Automate DataRobot with Tray.ai
Create a project, create a dataset from a file and update a use case in DataRobot. Connect DataRobot to the rest of your AI stack with Tray.ai.
What can you do with DataRobot on Tray.ai?
DataRobot is an AI platform for building, deploying, and monitoring machine learning models and generative AI applications, with automated modeling and governance tools. Tray.ai connects to DataRobot through the HTTP Connector, so your workflows can call the DataRobot API alongside the rest of your stack.
- Launch a batch prediction job each night on new accounts, then write churn scores to your CRM.
- Create a dataset from a file each time finance drops a new export in your shared storage.
- Download scored data after a prediction run and load it into your data warehouse for reporting.
- Connects through
- HTTP Connector
- Authentication
- A bearer token
- Base URL
- https://app.datarobot.com/api/v2
Set it up
Connect DataRobot to Tray.ai
Each step uses DataRobot's own API details, from its documentation.
Step 1
Save DataRobot's API token
Save the token DataRobot issues as a Tray.ai authentication. The HTTP Client sends it as a bearer token on every call. The token stays out of the workflow and out of the logs.
Step 2
Point the HTTP Client at the API
Add an HTTP Client step and use https://app.datarobot.com/api/v2 as the base URL. Or paste a cURL example from DataRobot's API docs, and Tray.ai fills in the method, URL, and headers.
Step 3
Start with “List projects”
It's one of 15 documented actions, under Projects. The response comes back as data the next step can map into your other apps.
Step 4
Hand it to an AI agent
Wrap “Create a project” and “Update a project” in workflows, and Tray.ai's Agent Gateway for MCP publishes them as governed tools Claude and other AI agents can call.
Give your AI agents DataRobot tools
Build an MCP server on DataRobot in Agent Gateway and choose which actions your agents can call. Every call runs with access control and an audit trail. How Agent Gateway works
- List projects
- List datasets
- List batch prediction jobs
- List use cases
- Create a project
- Update a project
- Delete a project
- Create a dataset from a file
What the DataRobot API covers
4 resources and 15 documented actions, each one a call the HTTP Connector can make from a Tray.ai workflow. Connecting it takes a few clicks: here's how.
Projects
- List projects
- Create a project
- Update a project
- Delete a project
Datasets
- List datasets
- Create a dataset from a file
- Create a dataset from a URL
- Delete a dataset
Batch predictions
- List batch prediction jobs
- Launch a batch prediction job
- Cancel a batch prediction job
- Download scored data
Use cases
- List use cases
- Update a use case
- Delete a use case
Checked against DataRobot's own documentation on 2026-10-22
How Tray.ai makes this work
DataRobot plugs into the whole Tray.ai platform
Intelligent Integration
Integrate and automate across 10,100+ apps, databases, APIs, and services with visual workflows, error handling, and observability.
Learn more →Agent Builder
Build AI agents that read, write, and take action in DataRobot — with guardrails, audit, and human-in-the-loop.
Learn more →Agent Gateway for MCP
Expose DataRobot actions as governed MCP tools — observable, rate-limited, authenticated.
Learn more →Tray Helix
Build apps on DataRobot data with your AI assistant, then deploy, run, and govern them on Tray.ai.
Learn more →More ai apps on Tray.ai
Dedicated connectors and other apps Tray.ai reaches in the same category. See every ai connector →
.DkNUKaKx_ZVgXRf.webp?dpl=dpl_ARtVL4739pNJnxC8yxqCNToe4mN7){kind=small}
Frequently asked questions
What can a Tray.ai workflow do in DataRobot?
+
The DataRobot API documents 15 actions across 4 resources (Projects, Datasets, Batch predictions, Use cases). For example: List projects; List datasets; List batch prediction jobs. A workflow can make any documented call through the HTTP Connector.
How does Tray.ai authenticate with DataRobot?
+
The DataRobot API uses a bearer token. You save it once as a Tray.ai authentication, and the HTTP Connector adds it to every request.
See DataRobot working against your stack.
We'll walk through a tailored demo with your systems plugged in.
Thanks — someone from our team will be in touch soon.