start_cluster · Databricks MCP Server MCP: Risk & Policy

WHAT IT DOES

What start_cluster does on Databricks MCP Server

AI agents invoke start_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 IT NEEDS A POLICY

Why start_cluster needs a policy

This tool executes an operation with external effects (cluster startup) that depend on the cluster_id argument provided by the agent. While not destructive or financial, it triggers infrastructure operations whose consequences (resource consumption, job execution, cost incursion) depend on what was previously configured on that cluster.

From the tool's definition Tool name 'start_cluster' and description 'Start a terminated Databricks cluster' indicates triggering cluster infrastructure operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_cluster Rate-limited

start_cluster stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Databricks MCP Server, so you can run agents against it safely.

FAQ

Questions about start_cluster

What does the start_cluster tool do? +

Start a terminated Databricks cluster with parameter: cluster_id (required). It is categorised as a Execute tool in the Databricks MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_cluster? +

Register the Databricks MCP Server MCP server in PolicyLayer and add a rule for start_cluster: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Databricks MCP Server. Nothing to install.

What risk level is start_cluster? +

start_cluster is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit start_cluster? +

Yes. Add a rate_limit block to the start_cluster rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block start_cluster completely? +

Set action: deny in the PolicyLayer policy for start_cluster. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides start_cluster? +

start_cluster is provided by the Databricks MCP Server MCP server (robkisk/databricks-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.