AI agents call pod_terminate to permanently remove resources in Prime Intellect — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Terminating a GPU pod is an irreversible destructive action: the pod is stopped and deleted, any in-memory or ephemeral storage is lost, and the action cannot be undone. The server description explicitly lists 'terminate' as a core capability. Even though the description field is empty, the tool name and server context make the classification clear.
From the tool's definition Tool name 'pod_terminate' on a server described as enabling agents to 'rent, drive, and terminate Prime Intellect GPU pods'. Termination of a cloud GPU pod is irreversible — it destroys the running instance and any ephemeral data.
Documented attack patterns abuse exactly the kind of access pod_terminate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Prime Intellect, and nothing reaches the server without passing your rules. This is the rule we recommend for pod_terminate:
{
"version": "1",
"default": "deny",
"hide": [
"pod_terminate"
]
}pod_terminate 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.
pod_terminate. It is categorised as a Destructive tool in the Prime Intellect MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Prime Intellect MCP server in PolicyLayer and add a rule for pod_terminate: 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 Prime Intellect. Nothing to install.
pod_terminate 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 pod_terminate 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 pod_terminate. 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.
pod_terminate is provided by the Prime Intellect MCP server (kvrancic/prime-intellect-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Prime Intellect, 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.
9 Prime Intellect tools catalogued and risk-classified — across an index of 43,000+ MCP servers.