Databricks MCP integration
Databricks workspace integration for SQL Statement Execution API 2.0, Jobs API 2.2, Unity Catalog API 2.1, and Workspace API 2.0.
Sign in, add Databricks in Apps, then choose the account your AI can use.
Tools
| Name | Description |
|---|---|
validate_connectionValidate credentials with a low-impact Databricks Workspace API 2.0 get-status request on the workspace root. | Validate credentials with a low-impact Databricks Workspace API 2.0 get-status request on the workspace root. |
execute_sql_statementExecute a Databricks SQL Statement Execution API 2.0 request against a SQL warehouse. SQL is read-only by default so agents do not mutate data unless explicitly allowed. | Execute a Databricks SQL Statement Execution API 2.0 request against a SQL warehouse. SQL is read-only by default so agents do not mutate data unless explicitly allowed. |
get_sql_statementGet status, manifest, and the first result chunk for a Databricks SQL Statement Execution API 2.0 statement. | Get status, manifest, and the first result chunk for a Databricks SQL Statement Execution API 2.0 statement. |
get_sql_result_chunkFetch a specific result chunk from a completed Databricks SQL Statement Execution API 2.0 statement. | Fetch a specific result chunk from a completed Databricks SQL Statement Execution API 2.0 statement. |
cancel_sql_statementCancel a running Databricks SQL Statement Execution API 2.0 statement and poll get_sql_statement for the terminal state. | Cancel a running Databricks SQL Statement Execution API 2.0 statement and poll get_sql_statement for the terminal state. |
list_jobsList Databricks Jobs API 2.2 jobs visible to the token, with pagination fields preserved for agents. | List Databricks Jobs API 2.2 jobs visible to the token, with pagination fields preserved for agents. |
get_jobGet a single Databricks Jobs API 2.2 job definition by job_id. | Get a single Databricks Jobs API 2.2 job definition by job_id. |
run_job_nowTrigger an existing Databricks job with Jobs API 2.2 run-now and return the run_id. Requires explicit confirmation so agents do not start compute accidentally. | Trigger an existing Databricks job with Jobs API 2.2 run-now and return the run_id. Requires explicit confirmation so agents do not start compute accidentally. |
cancel_job_runCancel a Databricks Jobs API 2.2 job run or task run. Requires explicit confirmation because cancellation changes run state. | Cancel a Databricks Jobs API 2.2 job run or task run. Requires explicit confirmation because cancellation changes run state. |
list_job_runsList Databricks Jobs API 2.2 runs in descending start-time order for monitoring and pagination. | List Databricks Jobs API 2.2 runs in descending start-time order for monitoring and pagination. |
get_job_runGet Databricks Jobs API 2.2 run metadata for a job run or task run. | Get Databricks Jobs API 2.2 run metadata for a job run or task run. |
get_job_run_outputRetrieve output and metadata for a single Databricks Jobs API 2.2 task run. Databricks returns only the first 5 MB of notebook output and logs. | Retrieve output and metadata for a single Databricks Jobs API 2.2 task run. Databricks returns only the first 5 MB of notebook output and logs. |
list_catalogsList Unity Catalog catalogs using Databricks Unity Catalog API 2.1. | List Unity Catalog catalogs using Databricks Unity Catalog API 2.1. |
get_catalogGet one Unity Catalog catalog by name using Databricks Unity Catalog API 2.1. | Get one Unity Catalog catalog by name using Databricks Unity Catalog API 2.1. |
list_schemasList schemas under a Unity Catalog catalog using Databricks Unity Catalog API 2.1. | List schemas under a Unity Catalog catalog using Databricks Unity Catalog API 2.1. |
get_schemaGet a Unity Catalog schema by full name, for example main.default. | Get a Unity Catalog schema by full name, for example main.default. |
list_tablesList tables and views under a Unity Catalog schema using Databricks Unity Catalog API 2.1. | List tables and views under a Unity Catalog schema using Databricks Unity Catalog API 2.1. |
get_tableGet a Unity Catalog table or view by full name, for example main.default.orders. | Get a Unity Catalog table or view by full name, for example main.default.orders. |
list_table_summariesList compact Unity Catalog table summaries using Databricks Unity Catalog API 2.1. | List compact Unity Catalog table summaries using Databricks Unity Catalog API 2.1. |
list_workspace_objectsList notebooks, directories, repos, and files under a workspace path using Databricks Workspace API 2.0. | List notebooks, directories, repos, and files under a workspace path using Databricks Workspace API 2.0. |
get_workspace_object_statusGet metadata for one workspace object with Databricks Workspace API 2.0 get-status. | Get metadata for one workspace object with Databricks Workspace API 2.0 get-status. |
export_workspace_objectExport a Databricks workspace notebook or file with Workspace API 2.0. Direct downloads are returned as base64 content. | Export a Databricks workspace notebook or file with Workspace API 2.0. Direct downloads are returned as base64 content. |
custom_api_callCall a Databricks REST API path on the configured workspace. Only relative /api/... paths are allowed; auth and headers are fixed by the connection. | Call a Databricks REST API path on the configured workspace. Only relative /api/... paths are allowed; auth and headers are fixed by the connection. |
Triggers
| Name | Description |
|---|---|
job_run_state_changedTriggers when a Databricks Jobs API run state changes. | Triggers when a Databricks Jobs API run state changes. |
latest_job_run_finishedTriggers when a Databricks job has a newly completed run. | Triggers when a Databricks job has a newly completed run. |
Quick Start
import { WeavzClient } from '@weavz-io/sdk'
const weavz = new WeavzClient({ apiKey: 'wvz_...' })
const result = await weavz.actions.execute('databricks', 'validate_connection', {
workspaceId: '550e8400-e29b-41d4-a716-446655440000',
integrationAlias: 'databricks',
input: { /* ... */ },
})Related Integrations
Works well with
Frequently Asked Questions
Is there a Databricks MCP server through Weavz?
Yes. Add the Databricks integration to a Weavz workspace, enable the actions you need and connect any required account. Weavz provides the workspace MCP endpoint in Tool Mode or Code Mode. The catalog currently lists 23 Databricks actions.
What can an AI agent do with Databricks?
Available actions include Validate Connection, Execute SQL Statement, Get SQL Statement, Get SQL Result Chunk, Cancel SQL Statement, and more. Your workspace exposes only the actions you enable. The agent also needs the intended account access and any required input values.
How do I connect Databricks to Claude or ChatGPT?
Use a compatible remote MCP client, add the Weavz connector and choose a workspace. Add Databricks, connect the required account and review the enabled actions. Client availability and account requirements vary; adding the connector does not authorize every app automatically.
Can I use Databricks through an API or SDK?
Yes, supported actions can run through the Weavz REST API, TypeScript SDK or Python SDK. Configure a workspace and the required connections, use scoped access, and pass the intended end-user context when acting for a customer.
What authentication does Databricks require?
The catalog lists custom credentials for Databricks. Use Hosted Connect to authorize the intended account. Required permissions, provider app access and available connection methods depend on the integration.
How do I review sensitive Databricks actions?
Limit enabled actions, scope credentials to the intended user and configure Human Gates for the operations that need review. A matching policy can pause a send, record change or other sensitive action for an approver before execution.
What limits or costs apply to Databricks?
Weavz plan limits apply to the actions and resources you use. The external provider may also require an account, a paid plan, API credits or specific permissions, and may enforce its own rate limits. Check current Weavz pricing and the provider’s terms before rollout.
What Databricks triggers are available?
The catalog lists 2 triggers, including Job Run State Changed, Latest Job Run Finished. Configure the trigger and your event handler before using incoming events to start work.
Connect Databricks in minutes
Get 20,000 free action executions every month. No credit card required.