samhavens/databricks-mcp-server
If you are the rightful owner of databricks-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.
The Databricks MCP Server is a Model Completion Protocol server that enables interaction with Databricks functionality through the MCP protocol, facilitating integration with LLM-powered tools.
Tools
Functions exposed to the LLM to take actions
list_clusters
List all Databricks clusters.
create_cluster
Create a new Databricks cluster.
terminate_cluster
Terminate a Databricks cluster.
get_cluster
Get information about a specific Databricks cluster.
start_cluster
Start a terminated Databricks cluster.
list_jobs
List all Databricks jobs.
run_job
Run a Databricks job.
create_job
Create a new job to run a notebook.
list_notebooks
List notebooks in a workspace directory.
export_notebook
Export a notebook from the workspace.
create_notebook
Create a new notebook in the workspace.
list_files
List files and directories in a DBFS path.
execute_sql
Execute a SQL statement and wait for completion (blocking).
execute_sql_nonblocking
Start SQL execution and return immediately with statement_id.
get_sql_status
Get status and results of a SQL statement by statement_id.
Prompts
Interactive templates invoked by user choice
No prompts
Resources
Contextual data attached and managed by the client