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.
This tool executes a command to start a computational pod in RunPod's infrastructure. While not destructive (the pod can be stopped), it initiates external operations with real-world effects (compute resource allocation, potential costs). The empty description lowers confidence slightly, but the context of pod management makes the Execute category appropriate.
From the tool's definition Tool name 'start-pod' combined with server description stating it 'Enables interaction with the RunPod REST API' for 'managing pods'. Starting a pod triggers external compute operations whose effects depend on pod configuration arguments.
Documented attack patterns abuse exactly the kind of access start-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 start-pod:
{
"version": "1",
"default": "deny",
"tools": {
"start-pod": {
"limits": [
{
"counter": "start-pod_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}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.
Free to start. No card required.
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.
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.
start-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 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.
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.
start-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.