Return locally-tracked pods that have run past max_lifetime_hours OR whose
AI agents call pod_check_runaway to retrieve information from Prime Intellect without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns status information about pods that exceed runtime thresholds. It performs read-only monitoring without modifying, terminating, or executing operations. While it provides operational awareness about resource costs, it does not directly commit financial obligations (that would be pod_create or pod_terminate).
From the tool's definition Tool name 'pod_check_runaway' and description 'Return locally-tracked pods that have run past max_lifetime_hours OR whose...' — the verb 'Return' indicates data retrieval.
Documented attack patterns abuse exactly the kind of access pod_check_runaway 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_check_runaway:
{
"version": "1",
"default": "deny",
"tools": {
"pod_check_runaway": {}
}
}pod_check_runaway is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Return locally-tracked pods that have run past max_lifetime_hours OR whose. It is categorised as a Read tool in the Prime Intellect MCP Server, which means it retrieves data without modifying state.
Register the Prime Intellect MCP server in PolicyLayer and add a rule for pod_check_runaway: 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_check_runaway is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the pod_check_runaway 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_check_runaway. 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_check_runaway 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.