databricks_restart_cluster

What databricks_restart_cluster does on Databricks MCP Server

AI agents invoke databricks_restart_cluster 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_restart_cluster is rated High

Cluster restart is an Execute category tool because it triggers an external operational action (restarting compute infrastructure) rather than simply reading data (Read), reversibly creating/modifying data (Write), or permanently destroying data (Destructive). The severity is high because a misused restart could disrupt data processing workloads, cause job failures, or impact production systems.

From the tool's definition Tool name 'databricks_restart_cluster' indicates it performs a cluster restart operation. The sibling tools on this server (databricks_cancel_run, databricks_create_cluster, databricks_cancel_all_runs) establish this as a Databricks compute management API.

The rule that runs databricks_restart_cluster 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_restart_cluster, this is the rule to start with:

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

Questions about databricks_restart_cluster