Connect Your AI Agent with Databricks for Slack

Integrate Databricks MCP server into your Slack workspace for instant access to your AI agent.

Back to MCP Servers
Databricks
Databricks
Databricks is the lakehouse company, helping data teams solve the world’s toughest problems.

Categories

Data Analytics

Available Tools

Tools that your AI agent can use through this MCP server to interact with Databricks

Upsert Vector Search Index Data

Upserts (inserts/updates) data into an existing vector search index. See the documentation

Update Job

Update an existing job. Only the fields that are provided will be updated. See the documentation

Sync Vector Search Index

Synchronize a Delta Sync vector search index in Databricks. See the documentation

Stop SQL Warehouse

Stops a SQL Warehouse by ID. See the documentation

Start SQL Warehouse

Starts a SQL Warehouse by ID. See the documentation

Set SQL Warehouse Permissions

Updates the permissions for a specific SQL Warehouse. See docs

Set SQL Warehouse Config

Updates the global configuration for SQL Warehouses. See the documentation

Set Job Permissions

Set permissions on a job. See the documentation

Scan Vector Search Index

Scans a vector search index and returns entries after the given primary key. See documentation

Run Job Now

Run a job now and return the id of the triggered run. See the documentation

Reset Job

Overwrite all settings for the given job. See the documentation

Repair Run

Re-run one or more tasks. See the documentation

Query Vector Search Index

Query a specific vector search index in Databricks. See the documentation

List Vector Search Indexes

Lists all vector search indexes for a given endpoint. See the documentation

List SQL Warehouses

Lists all SQL Warehouses available in the Databricks workspace. See the documentation

List Runs

Lists all runs available to the user. See the documentation

List Jobs

List all jobs using automatic pagination. See the documentation

List Endpoints

List all vector search endpoints. See the documentation

Get Vector Search Index

Retrieves details about a specific vector search index. See the documentation

Get SQL Warehouse

Retrieves details for a specific SQL Warehouse. See docs

Get SQL Warehouse Permissions

Retrieves the permissions for a specific SQL Warehouse. See the documentation

Get SQL Warehouse Config

Retrieves the global configuration for SQL Warehouses. See the documentation

Get Run

Retrieve the metadata of a run. See the documentation

Get Run Output

Retrieve the output and metadata of a single task run. See the documentation

Get Job

Retrieves the details for a single job. See the documentation

Get Job Permissions

Get permissions of a job. See the documentation

Get Endpoint

Get details of a specific vector search endpoint. See the documentation

Export Run

Export and retrieve the job run task. See the documentation

Edit SQL Warehouse

Edits the configuration of an existing SQL Warehouse. See the documentation

Delete Vector Search Index

Deletes a vector search index in Databricks. See the documentation

Delete Data from Vector Search Index

Deletes rows from a Direct Access vector index by primary-key values. See the documentation

Delete SQL Warehouse

Deletes a SQL Warehouse by ID. See the documentation

Delete Run

Delete a non-active run. Returns an error if the run is active. See the documentation

Delete Job

Delete a job. Deleted jobs cannot be recovered. See the documentation

Delete Endpoint

Delete a vector search endpoint. See the documentation

Create Vector Search Index

Creates a new vector search index in Databricks. See the documentation

Create SQL Warehouse

Creates a new SQL Warehouse in Databricks. See the documentation

Create Job

Create a job. See the documentation

Create Endpoint

Create a new vector search endpoint. See the documentation

Cancel Run

Cancel a job run. The run is canceled asynchronously, so it may still be running when this request completes. See the documentation

Cancel All Runs

Cancel all active runs for a job. The runs are canceled asynchronously, so it doesn't prevent new runs from being started. See the documentation