databricks_stop_pipeline

What databricks_stop_pipeline does on Databricks MCP Server

AI agents invoke databricks_stop_pipeline 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_stop_pipeline is rated High

Stopping a pipeline is an Execute action because it triggers an external operation that halts an ongoing computational process. It is not Destructive (the pipeline itself is not deleted, just stopped) or Write (no data is created/modified). The blast radius is high because an agent could disrupt critical data workflows by stopping important pipelines without authorization or context.

From the tool's definition Tool name is 'databricks_stop_pipeline' which indicates stopping a running data pipeline; sibling tools like databricks_cancel_run, databricks_cancel_statement, and databricks_cancel_all_runs demonstrate this server's pattern of execution control tools; the…

The rule that runs databricks_stop_pipeline 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_stop_pipeline, this is the rule to start with:

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

Questions about databricks_stop_pipeline