Connect Datarobot to AI agents

Connect Datarobot to Claude, Codex, Cursor, or other AI agents for your entire team. Metorial security, governance, observability, and gives your team a unified Magic MCP url to connect.

Supported Tools

get_project

Get Project

Retrieve detailed information about a specific DataRobot project including its configuration, target, stage, partition settings, and advanced options.

list_datasets

List Datasets

List datasets in the DataRobot AI Catalog. Returns metadata including name, size, row/column counts, and processing state.

get_deployment_monitoring

Get Deployment Monitoring

Retrieve monitoring data for a deployed model including service health statistics, accuracy metrics, data drift, and target drift. Choose which monitoring aspects to include.

make_predictions

Make Predictions

Make real-time predictions using a deployed model. Pass an array of data rows as key-value objects. Optionally include prediction explanations to understand why the model makes each prediction.

start_autopilot

Start Autopilot

Set the target variable and start Autopilot on an existing project. Autopilot automatically selects and trains the best predictive models for the specified target feature. Supports configuration of mode, metric, and advanced options.

get_deployment

Get Deployment

Retrieve detailed information about a specific model deployment including its health status, model information, capabilities, and configuration.

list_deployments

List Deployments

List all model deployments with their health status, importance, and prediction usage. Useful for monitoring deployed models across the organization.

create_deployment

Create Deployment

Deploy a trained model to production. Supports deploying from a learning model (by modelId) or from a registered model package (by modelPackageId). The deployment will be accessible for real-time or batch predictions.

manage_dataset

Create, Update, or Delete Dataset

Manage datasets in the AI Catalog. Create a new dataset from a URL, update an existing dataset's name, or delete a dataset.

list_models

List Models

List trained models in a DataRobot project, including the recommended model. Returns model types, training details, and performance metrics from the leaderboard.

manage_deployment

Update, Replace Model, or Delete Deployment

Manage an existing deployment. Update its label/description/importance, replace the champion model, or delete the deployment entirely.

list_model_packages

List Model Packages

List model packages in the Model Registry. Model packages are deployment-ready bundles that can be deployed, shared, or used to generate compliance documentation.

create_project

Create Project

Create a new DataRobot project from a dataset URL or an existing AI Catalog dataset. Optionally sets the target variable and starts Autopilot in one step.

register_model

Register Model

Register a trained model from a project leaderboard as a model package in the Model Registry. Registered model packages can then be deployed, shared, and used for compliance documentation.

list_projects

List Projects

List DataRobot projects with optional filtering. Returns project metadata including name, stage, target, and modeling configuration.

manage_project

Update or Delete Project

Update a project's name or delete a project entirely. Use action "update" to rename, or "delete" to soft-delete the project.

get_dataset

Get Dataset

Retrieve detailed information about a specific dataset in the AI Catalog including its schema, feature types, size, and processing state.

get_model

Get Model Details

Retrieve detailed information about a specific trained model including its type, metrics, training configuration, and optionally its feature impact scores.

More integrations teams use with Datarobot

GitHub

Manage repositories, issues, and pull requests. Create and configure branches, star repositories, review code, and merge changes. Automate CI/CD workflows with GitHub Actions, manage workflow runs, secrets, and artifacts. Track issues with labels, milestones, and assignees. Search across code, repositories, issues, and users. Manage organizations, teams, and memberships. Create and manage projects, gists, packages, deployments, and environments. Access security alerts including code scanning, secret scanning, and Dependabot alerts. Read and write file contents in repositories. Manage webhooks, notifications, and codespaces.

Sharepoint

Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Subscribe to webhooks for list and library change notifications. Retrieve site properties and search for sites across Microsoft 365.

Salesforce

Manage CRM data including Accounts, Contacts, Leads, Opportunities, Cases, and custom objects. Create, read, update, and delete records. Query data using SOQL and search across objects using SOSL. Perform bulk data operations for large-scale imports, exports, and migrations. Execute composite requests to batch multiple operations in a single API call. Access analytics, reports, and dashboards. Manage files and attachments associated with records. Interact with Chatter feeds, posts, and groups for social collaboration. Subscribe to real-time change events via Change Data Capture and Platform Events. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.

Airtable

Create, read, update, and delete records in Airtable bases and tables. Manage base schemas including creating tables and fields. Filter records using formulas, sort by fields, and scope queries to specific views. Upsert records to find, create, or update in a single call. Upload attachments to records, read and write record comments, list accessible bases, and receive real-time base change events through webhooks.

Bitbucket

Manage Git repositories, pull requests, and CI/CD pipelines on Bitbucket Cloud. Create, fork, and configure repositories within workspaces and projects. Create, review, approve, merge, and decline pull requests with inline code comments. Browse source code, list commits, and manage branches and tags. Track issues with the built-in issue tracker. Trigger, monitor, and manage Bitbucket Pipelines. List workspace members, configure repository default reviewers and branch restrictions, create and manage repository webhooks, and search code across repositories.

Heroku

Deploy, manage, and scale applications on Heroku's cloud platform. Create and configure apps, scale dynos, provision add-ons (databases, caching, etc.), manage configuration variables, build and release code, add custom domains and SSL certificates, manage collaborators and team permissions, configure pipelines for continuous delivery, set up log drains, and sync data with Salesforce via Heroku Connect. Subscribe to webhooks for real-time notifications on app changes, builds, releases, dyno lifecycle events, and more.

Technical notes for Datarobot

Create and manage machine learning projects, train predictive models, and deploy them to production. Run AutoML/Autopilot to automatically select and build best-fit models. Upload and manage datasets in the AI Catalog. Deploy custom models (Python, R, Java) as real-time or batch prediction endpoints. Monitor deployments for data drift, accuracy, and service health. Generate prediction explanations, feature impact scores, and compliance documentation. Manage registered models, credentials, and time series projects. Subscribe to webhook events for project, dataset, and deployment lifecycle changes.

Connect Datarobot to production AI agents

See how Metorial gives Datarobot access the governance, tracing, and security controls teams need.

Frequently asked questions

Common questions about connecting Datarobot to AI agents with Metorial.

  1. Can Metorial connect Datarobot to AI agents?
    Yes. Metorial connects AI agents to Datarobot through a governed integration layer, so teams can use the provider while keeping access controlled and observable.
  2. Metorial is MCP compatible and lets teams expose approved provider tools to MCP-capable agents and clients through a controlled access layer.
  3. Metorial applies policies across users, groups, providers, agents, and individual tools, then records the context around every agent interaction.
  4. Yes. Metorial records provider activity so teams can inspect tool calls, troubleshoot integrations, and give security teams the visibility they need.