Databricks
Databricks connector for managing clusters, jobs, job runs, SQL warehouses, SQL statement execution, and workspace objects across any Databricks deployment (AWS, Azure, GCP).
Categories: Data, Analytics, SQL, Infrastructure
What you can ask
- List the 10 most recent failed jobs in the
prodworkspace and surface the error. - Run the
nightly_etljob and notify #data-eng when it finishes. - Show me clusters with idle time >2 hours so we can shut them down.
Set up
Databricks connects with credentials from your Databricks account. Have these values ready:
- Workspace URL
- Personal access token
- Go to Organization > Connectors and find Databricks.
- Click Enable and choose which tools to allow.
- Each member enters their own values the first time they use it.
To use one account for the whole organization, turn on Share one connection with everyone. Every member's agents then act as that account, with exactly the access it has.
Tools
Databricks offers 48 tools. Admins choose which ones agents can use. See Tool permission groups.
Read (28)
View and search information without changing it.
| Tool | What it does |
|---|---|
ask_genie | Ask a natural language question about your data using Databricks Genie. |
execute_sql_statement_readonly | Run read-only SQL on a Databricks SQL warehouse: SELECT, WITH, SHOW, DESCRIBE, EXPLAIN, VALUES, LIST. |
export_notebook | Export a notebook's content from the workspace. |
get_cluster | Get detailed information about a specific Databricks cluster including state, configuration, and resource allocation. |
get_cluster_events | Get events for a cluster to diagnose issues. |
get_current_user | Get the current authenticated Databricks user and their workspace home directory. |
get_genie_message | Get the status and results of a Genie message. |
get_job | Get detailed information about a specific Databricks job including tasks, schedule, and configuration. |
get_job_run | Get detailed information about a specific job run including state, timing, and task details. |
get_job_run_output | Get the output of one task run: notebook results, SQL output, logs, error traces. |
get_sql_statement | Get the status and results of a SQL statement execution. |
get_sql_warehouse | Get detailed information about a specific SQL warehouse including state, size, cluster count, and active sessions. |
get_table_info | Get detailed information about a table including column definitions, types, and properties. |
get_workspace_object_status | Get metadata about a workspace object including type, language (for notebooks), and timestamps. |
list_catalogs | List all catalogs in Unity Catalog. |
list_cluster_options | List the Spark runtime versions and node types this workspace accepts for create_cluster. |
list_clusters | List all clusters in the Databricks workspace. |
list_genie_spaces | List available Genie spaces (rooms). |
list_job_runs | List job runs in the Databricks workspace. |
list_jobs | List jobs in the Databricks workspace with optional name filter and pagination. |
list_schemas | List schemas within a Unity Catalog catalog. |
list_serving_endpoints | List all model serving endpoints in the workspace. |
list_sql_warehouses | List all SQL warehouses in the Databricks workspace. |
list_tables | List tables within a Unity Catalog schema. |
list_workspace | List objects in a Databricks workspace directory. |
query_serving_endpoint | Query a model serving endpoint: chat completions (messages), embeddings or classic models (inputs). |
query_vector_index | Query a vector search index using text or a vector. |
validate_credential | Validate Databricks credentials. |
Write (7)
Create or send data.
| Tool | What it does |
|---|---|
create_cluster | Create a new Databricks cluster. |
create_job | Create a new Databricks job with one or more tasks. |
create_sql_warehouse | Create a new Databricks SQL warehouse. |
create_vector_search_endpoint | Create a vector search endpoint to host vector search indexes. |
create_vector_search_index | Create a vector search index on an endpoint. |
run_job_now | Trigger an immediate run of a Databricks job. |
run_notebook | Submit a one-time notebook run. |
Delete or overwrite (13)
Remove or replace existing data.
| Tool | What it does |
|---|---|
cancel_job_run | Cancel an active job run. |
cancel_sql_statement | Cancel a running SQL statement execution. |
delete_job | Permanently delete a Databricks job. |
delete_vector_search_endpoint | Delete a vector search endpoint. |
delete_vector_search_index | Delete a vector search index. |
delete_workspace_object | Delete a workspace object (notebook, file, or directory). |
execute_sql_statement | Execute a SQL statement that changes data or schema (INSERT, UPDATE, DELETE, MERGE, CREATE, DROP) on a SQL warehouse. |
import_notebook | Create or overwrite a notebook in the workspace. |
repair_run | Re-run failed tasks in a completed job run without re-running succeeded ones. |
start_cluster | Start a terminated Databricks cluster. |
start_sql_warehouse | Start a stopped SQL warehouse. |
stop_sql_warehouse | Stop a running SQL warehouse. |
terminate_cluster | Terminate a running Databricks cluster. |