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.
Terminating a cluster stops all running workloads, loses ephemeral state, and requires provisioning a new cluster to recover functionality. This is a destructive, non-reversible action with high blast radius in production environments.
From the tool's definition 'Terminate a cluster' — terminating a cluster is an irreversible stop operation that destroys the running cluster state, any in-memory data, and active sessions. It cannot be undone (a new cluster must be created).
Documented attack patterns abuse exactly the kind of access terminate_cluster gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Databricks MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for terminate_cluster:
{
"version": "1",
"default": "deny",
"hide": [
"terminate_cluster"
]
}terminate_cluster disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Terminate a cluster. 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.
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.
terminate_cluster is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
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.
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.
terminate_cluster is provided by the Databricks MCP Server MCP server (markov-kernel/databricks-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Databricks MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
38 Databricks MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.