Databricks MCP Server
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_clustersC | List all Databricks clusters |
| create_clusterC | Create a new Databricks cluster with parameters: cluster_name (required), spark_version (required), node_type_id (required), num_workers, autotermination_minutes |
| terminate_clusterC | Terminate a Databricks cluster with parameter: cluster_id (required) |
| get_clusterC | Get information about a specific Databricks cluster with parameter: cluster_id (required) |
| start_clusterC | Start a terminated Databricks cluster with parameter: cluster_id (required) |
| list_jobsC | List all Databricks jobs |
| run_jobC | Run a Databricks job with parameters: job_id (required), notebook_params (optional) |
| list_notebooksC | List notebooks in a workspace directory with parameter: path (required) |
| export_notebookC | Export a notebook from the workspace with parameters: path (required), format (optional, one of: SOURCE, HTML, JUPYTER, DBC) |
| list_filesC | List files and directories in a DBFS path with parameter: dbfs_path (required) |
| execute_sqlC | Execute a SQL statement with parameters: statement (required), warehouse_id (required), catalog (optional), schema (optional) |
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 11 tools
Each tool has a distinct purpose with clear boundaries: cluster management (create, get, list, start, terminate), SQL execution, notebook operations (export, list), file listing, and job operations (list, run). No overlapping functionality exists, making tool selection straightforward for an agent.
All tools follow a consistent verb_noun pattern (e.g., create_cluster, execute_sql, list_files) using snake_case throughout. This predictable naming convention enhances readability and usability for agents.
With 11 tools, the server is well-scoped for Databricks operations, covering clusters, SQL, notebooks, files, and jobs. Each tool serves a clear purpose without redundancy, making the count appropriate for the domain.
The toolset provides strong coverage for core Databricks workflows, including cluster lifecycle, SQL execution, notebook/file management, and job operations. Minor gaps exist, such as missing notebook creation or job update tools, but agents can work around these with available operations.