databricks-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| databricks_queryA | Execute Databricks SQL query (supports SELECT, SHOW, DESCRIBE, CREATE, ALTER). INSERT, UPDATE, DELETE, DROP and other destructive operations are blocked. Args: sql_query: SQL query statement (preferred parameter) sql: SQL query statement (fallback for backward compatibility) Returns: Query results as list of dicts |
| list_catalogsB | List all catalogs |
| list_schemasC | List schemas in the specified catalog |
| list_tablesC | List tables in the specified schema |
| get_table_schemaC | Get table structure (DESCRIBE EXTENDED) |
| search_tablesC | Search tables by name (using information_schema) |
| get_table_historyC | View Delta table change history (DESCRIBE HISTORY) |
| get_table_detailC | View Delta table details (DESCRIBE DETAIL) |
| get_grantsB | View object permissions (SHOW GRANTS) Args: securable_type: Object type (TABLE, SCHEMA, CATALOG, VOLUME, etc.) full_name: Full object name (catalog.schema.table format) |
| list_volumesC | List Unity Catalog Volumes |
| get_table_lineageA | Get table lineage (upstream/downstream tables and related notebooks/jobs) Args: catalog: Catalog name schema: Schema name table: Table name include_notebooks: Include notebook/job associations (slower) limit: Max rows to return (default 50) Returns: Dict with upstream, downstream tables and optionally notebook/job info |
| list_jobsD | List Jobs |
| get_jobD | Get job details |
| list_job_runsC | List job run history |
| get_job_runD | Get run details |
| list_pipelinesB | List Delta Live Tables Pipelines |
| get_pipelineD | Get pipeline status |
| list_pipeline_updatesC | List pipeline update history |
| list_query_historyB | List SQL query history Args: warehouse_id: (Optional) Filter by specific warehouse user_id: (Optional) Filter by specific user start_time: (Optional) Start time in local format "YYYY-MM-DD HH:MM:SS" end_time: (Optional) End time in local format "YYYY-MM-DD HH:MM:SS" limit: Number of results to return |
| list_warehousesB | List SQL Warehouses |
| list_clustersC | List Clusters |
| list_workspaceC | List Workspace directory contents |
| get_cluster_metricsB | Get cluster CPU/Memory/Network/Disk metrics Data source: system.compute.node_timeline (one record per minute) Args: cluster_id: Cluster ID start_time: Start time (ISO format), defaults to last 1 hour end_time: End time (ISO format), defaults to now limit: Max number of records to return, default 60 (1 hour) Returns: Metrics time series and summary statistics |
| get_cluster_eventsB | Get cluster event history (start, terminate, resize, errors, etc.) Args: cluster_id: Cluster ID limit: Max number of records to return Returns: Event list (time in local timezone) |
| get_run_task_metricsB | Get job run task execution time details Args: run_id: Job Run ID Returns: Task setup/execute/cleanup times (time in local timezone) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 25 tools
Most tools have distinct purposes targeting specific Databricks resources (clusters, jobs, tables, etc.), but some overlap exists. For example, get_table_detail, get_table_schema, and get_table_history all focus on table metadata with potentially unclear boundaries for an agent. However, descriptions help differentiate them by specifying different aspects (detail vs. schema vs. history).
Tool names follow a highly consistent verb_noun pattern throughout, with clear and predictable conventions. All tools use either 'get_', 'list_', or 'search_' prefixes followed by the resource name (e.g., get_cluster_events, list_jobs, search_tables), making them easily readable and systematic.
With 25 tools, the count is borderline high for a single server, potentially overwhelming for an agent. While Databricks is a complex platform, this many tools might indicate fragmentation or redundancy, such as multiple table-related tools that could be consolidated. It feels heavy but not extreme.
The tool set provides broad coverage for monitoring and querying Databricks resources, including clusters, jobs, tables, pipelines, and more. Minor gaps exist, such as lack of create/update/delete operations for many resources (e.g., no create_cluster or delete_job), but agents can work around this with the provided query tool for some operations. Core read and list functionalities are well-covered.