Connect Databricks to AI agents

Connect Databricks 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.

Deploy DatabricksBook a demo

Supported Tools

Tools22Triggers2

execute_sql

Execute SQL

Execute a SQL statement on a SQL warehouse and return the results. Supports catalog and schema context, and can wait for completion or return a statement ID for asynchronous polling.

list_experiments

List MLflow Experiments

List MLflow experiments in the workspace. Experiments are containers for organizing ML runs.

manage_secrets

Manage Secrets

Manage secret scopes and secrets. Create/delete scopes, put/delete secrets, or list scopes and secret keys. Secret values cannot be read back — only metadata is returned.

list_pipelines

List Pipelines

List Delta Live Tables pipelines in the workspace. Optionally filter by name or other criteria.

get_job_run

Get Job Run

Retrieve details and status of a specific job run, including task states, timing, and output. Can also list recent runs for a given job.

manage_job

Manage Job

Create, update, or delete a multi-task workflow job. Supports notebook, Python, and SQL task types with dependencies, scheduling, and notification settings.

browse_workspace

Browse Workspace

List notebooks, folders, and other objects in a workspace directory. Can also get the status (metadata) of a specific workspace object.

list_warehouses

List SQL Warehouses

List all SQL warehouses in the workspace with their status and configuration.

manage_warehouse

Manage SQL Warehouse

Create, start, stop, or delete a SQL warehouse. SQL warehouses are compute resources for running SQL queries in Databricks SQL.

browse_catalog

Browse Unity Catalog

Navigate the Unity Catalog hierarchy: list catalogs, schemas within a catalog, tables within a schema, or get details of a specific table. Provides governance metadata including owners, comments, and data types.

manage_pipeline

Manage Pipeline

Create, start, stop, or delete Delta Live Tables pipelines. Pipelines define declarative data transformations as directed acyclic graphs.

search_runs

Search MLflow Runs

Search for MLflow runs across one or more experiments. Filter by metrics, parameters, and tags using the MLflow search syntax. Returns run metadata, metrics, and parameters.

manage_cluster

Manage Cluster

Create, edit, start, restart, stop, or permanently delete an Apache Spark cluster. To **create** a new cluster, omit `clusterId` and provide `clusterName`, `sparkVersion`, and `nodeTypeId`. To **edit** an existing cluster, provide `clusterId` along with the fields to update. To **start/restart/stop/delete**, provide `clusterId` and the corresponding `action`.

manage_dbfs

Manage DBFS

Interact with the Databricks File System (DBFS). List, read, upload, create directories, and delete files or folders.

list_jobs

List Jobs

List jobs defined in the workspace. Optionally filter by name and expand task details.

manage_notebook

Manage Notebook

Import, export, or delete notebooks and create workspace directories. Use **import** to upload notebook content (base64-encoded). Use **export** to download a notebook as a Slate attachment. Use **delete** to remove a notebook or folder.

query_serving_endpoint

Query Serving Endpoint

Send an inference request to a model serving endpoint. Works with both custom ML models and Foundation Model APIs. The request format follows OpenAI-compatible chat/completions or generic model input schemas.

run_job

Run Job

Trigger an immediate run of an existing job, optionally with override parameters. Also supports cancelling a running job run.

list_clusters

List Clusters

List all available Apache Spark clusters in the workspace. Returns cluster details including state, configuration, and scaling settings.

list_serving_endpoints

List Serving Endpoints

List all model serving endpoints in the workspace. Serving endpoints host ML models and foundation models as REST APIs.

manage_files

Manage Files

Manage files and directories with the current Databricks Files API for workspace files and Unity Catalog Volumes. Supports listing directories, creating and deleting directories, uploading files, downloading files as Slate attachments, and deleting files.

manage_vector_search

Manage Vector Search

Manage and query Databricks Vector Search endpoints and indexes. Supports listing, getting, creating, and deleting endpoints; listing and getting indexes; deleting indexes; and querying an index with text or vector input.

More integrations teams use with Databricks

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 Databricks

Manage Databricks workspaces, clusters, jobs, and data assets. Create, start, stop, and configure Apache Spark clusters. Orchestrate multi-task workflows and data pipelines with scheduled or triggered jobs. Execute SQL statements on SQL warehouses. Manage Unity Catalog resources including catalogs, schemas, tables, and volumes for data governance. Track ML experiments, manage model registry, and deploy model serving endpoints. Create and manage vector search indexes. Import, export, and organize notebooks and workspace files. Upload and download files via DBFS and Unity Catalog Volumes. Manage users, groups, service principals, and permissions. Create and publish Lakeview dashboards. Share data across organizations with Delta Sharing. Store and manage secrets for secure credential access. Receive webhook notifications for model registry events and job lifecycle events.

Connect Databricks to production AI agents

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

Book a demoDeploy Databricks

Frequently asked questions

Common questions about connecting Databricks to AI agents with Metorial.

  1. Can Metorial connect Databricks to AI agents?
    Yes. Metorial connects AI agents to Databricks 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.