Create a new GPU/CPU pod on RunPod. If the user does not specify an image, recommend the
AI agents use create-pod to create or update resources in RunPod MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your RunPod MCP Server environment.
This tool creates a new compute pod (GPU/CPU instance) on RunPod, which is a Write operation. However, it carries high severity because spinning up GPU/CPU instances can incur significant cloud compute costs if misused by an AI agent, and provisioning infrastructure has broad operational impact.
From the tool's definition Create a new GPU/CPU pod on RunPod
Documented attack patterns abuse exactly the kind of access create-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 create-pod:
{
"version": "1",
"default": "deny",
"tools": {
"create-pod": {
"limits": [
{
"counter": "create-pod_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create-pod stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a new GPU/CPU pod on RunPod. If the user does not specify an image, recommend the. It is categorised as a Write tool in the RunPod MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the RunPod MCP Server MCP server in PolicyLayer and add a rule for create-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.
create-pod is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create-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 create-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.
create-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.