databricks_find_and_start_warehouse

What databricks_find_and_start_warehouse does on Databricks MCP Server

AI agents invoke databricks_find_and_start_warehouse to trigger actions in Databricks MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Why databricks_find_and_start_warehouse is rated High

Starting a SQL warehouse is an operational action that provisions or activates compute infrastructure. It is not merely reading data, nor does it delete or modify data irreversibly. It falls under Execute because it triggers an external compute operation. Misuse could result in unexpected resource consumption and cost implications, but it is not directly financial (no money movement) or destructive.

From the tool's definition 'Find an available SQL warehouse and start it if needed' — the tool triggers an external operation (starting a warehouse/compute resource) whose effect depends on the current state of the environment.

The rule that runs databricks_find_and_start_warehouse safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Databricks MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For databricks_find_and_start_warehouse, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "databricks_find_and_start_warehouse": {
      "limits": [
        {
          "counter": "databricks_find_and_start_warehouse_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about databricks_find_and_start_warehouse