High-risk tools in Databricks MCP Server
7 of the 38 tools in Databricks MCP Server are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
cancel_runExecuteCancel a job run with parameter: run_id
-
execute_sqlExecuteExecute a SQL statement with parameters: statement (required), warehouse_id (optional - uses DATABRICKS_WAREHOUSE_ID env var if not provided), catalog (optional), schema (optional)
-
install_libraryExecuteInstall a library on a cluster with parameters: cluster_id, libraries
-
run_jobExecuteRun a Databricks job with parameters: job_id (required), notebook_params (optional)
-
run_notebookExecuteSubmit a one-time notebook run with parameters: notebook_path (required), existing_cluster_id (optional), base_parameters (optional)
-
start_clusterExecuteStart a terminated Databricks cluster with parameter: cluster_id (required)
-
sync_repo_and_run_notebookExecutePull a repo then run a notebook. Parameters: repo_id, notebook_path, existing_cluster_id (optional), base_parameters (optional)
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.