AI agents invoke stop-pod to trigger actions in RunPod 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.
Although the description is empty, the tool name and server context clearly indicate this stops a running pod. Stopping a pod is a state-change operation that interrupts workloads and can disrupt services, but it is reversible (pods can be restarted). This does not qualify as Destructive (which is irreversible deletion) but exceeds Write because it triggers external compute infrastructure effects.
From the tool's definition Tool name 'stop-pod' indicates termination of a running pod instance. Within the RunPod MCP server context (managing pods, endpoints, templates, network volumes, and container registry), stopping a pod triggers external operations that halt compute resources.
Documented attack patterns abuse exactly the kind of access stop-pod gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and RunPod MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for stop-pod:
{
"version": "1",
"default": "deny",
"tools": {
"stop-pod": {
"limits": [
{
"counter": "stop-pod_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}stop-pod 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.
Free to start. No card required.
stop-pod. It is categorised as a Execute tool in the RunPod MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the RunPod MCP Server MCP server in PolicyLayer and add a rule for stop-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.
stop-pod is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the stop-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 stop-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.
stop-pod is provided by the RunPod MCP Server MCP server (runpod/runpod-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 36 RunPod MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
36 RunPod MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.