start-pod · RunPod MCP Server MCP: Risk & Policy

WHAT IT DOES

What start-pod does on RunPod MCP Server

AI agents invoke start-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.

WHY IT NEEDS A POLICY

Why start-pod needs a policy

Starting a pod is an Execute action—it runs/triggers an external operation (pod startup) on cloud infrastructure whose effects depend on arguments (pod ID). The severity is high because a compromised agent could launch expensive compute resources, consume credits, or enable unauthorized workloads.

From the tool's definition Tool name 'start-pod' indicates it triggers an external operation (starting a RunPod container) whose effects depend on which pod is targeted. The server manages pods, endpoints, and compute resources via REST API.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start-pod Rate-limited

start-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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start-pod": {
      "limits": [
        {
          "counter": "start-pod_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches RunPod MCP Server, so you can run agents against it safely.

FAQ

Questions about start-pod

What does the start-pod tool do? +

start-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.

How do I enforce a policy on start-pod? +

Register the RunPod MCP Server MCP server in PolicyLayer and add a rule for start-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.

What risk level is start-pod? +

start-pod is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit start-pod? +

Yes. Add a rate_limit block to the start-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.

How do I block start-pod completely? +

Set action: deny in the PolicyLayer policy for start-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.

What MCP server provides start-pod? +

start-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.