terminate_cluster

Terminate a Databricks cluster with parameter: cluster_id (string, required)

SERVERDatabricks MCP Server SOURCEandresgarciasobrado91/databricks-mcp-server

Critical RISK CLASS

Category Destructive

Parameters 00 required

Recommended Hiddensee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/andresgarciasobrado91-databricks-mcp-server/terminate-cluster.md

WHAT IT DOES

What terminate_cluster does on Databricks MCP Server

AI agents call terminate_cluster to permanently remove resources in Databricks MCP Server, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

RISK

Why terminate_cluster is rated Critical

Terminating a cluster kills all active sessions, jobs, and computations running on it. While the cluster configuration may be retained and a new cluster could be recreated, the running state, in-memory data, and active workloads are permanently destroyed. This is an irreversible destructive action with high blast radius since it can disrupt production workloads and cause data loss for in-progress jobs.

From the tool's definition 'Terminate a Databricks cluster' — termination stops and destroys the running cluster, which is an irreversible action that ends all running workloads on that cluster.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs terminate_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 terminate_cluster, this is the rule to start with:

terminate_cluster Hidden

terminate_cluster is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "terminate_cluster"
  ]
}

RESTRICT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Databricks MCP Server, apply this rule, and every terminate_cluster call is checked against it from then on.

FAQ

Questions about terminate_cluster

What does the terminate_cluster tool do? +

Terminate a Databricks cluster with parameter: cluster_id (string, required). It is categorised as a Destructive tool in the Databricks MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on terminate_cluster? +

Register the Databricks MCP Server MCP server in PolicyLayer and add a rule for terminate_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 terminate_cluster? +

terminate_cluster is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit terminate_cluster? +

Yes. Add a rate_limit block to the terminate_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 terminate_cluster completely? +

Set action: deny in the PolicyLayer policy for terminate_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 terminate_cluster? +

terminate_cluster is provided by the Databricks MCP Server MCP server (andresgarciasobrado91/databricks-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Databricks MCP Server, and thousands of servers like it.

This server

All 15 Databricks MCP Server tools → Critical-risk tools on this server →

Across the catalogue

All critical-risk MCP tools → The MCP Attack Database →

Guides

Govern database agents →Blast radius →Tool call approval →