delete-pod
AI agents call delete-pod to permanently remove resources in RunPod MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool deletes a pod, which is an infrastructure resource. Pod deletion removes compute instances and their associated state, which cannot be undone. This matches the Destructive category definition of 'irreversibly deletes or overwrites data, or actions that cannot be undone.' While the description is empty, the tool name is unambiguous.
From the tool's definition Tool name is 'delete-pod' which indicates permanent removal of a pod resource. The server manages pods through RunPod REST API, and deletion operations are irreversible.
Attacks that exploit this kind of access
delete-pod. It is categorised as a Destructive tool in the RunPod MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the RunPod MCP Server MCP server in PolicyLayer and add a rule for delete-pod: 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 RunPod MCP Server. Nothing to install.
delete-pod 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 delete-pod 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 delete-pod. 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.
delete-pod is provided by the RunPod MCP Server MCP server (niel-runpod/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →