pod_create

THE RISK

Critical Risk

Why pod_create needs a policy

Creating a GPU pod on this platform directly incurs costs (rental charges), making this a Financial action. The server description explicitly mentions spend caps and autonomous provisioning of paid cloud resources. Misuse could rapidly exhaust funds, warranting critical severity.

From the tool's definition Tool name 'pod_create' on a server described as enabling agents to 'rent, drive, and terminate Prime Intellect GPU pods with hard spend caps' — creation of a GPU pod constitutes renting cloud resources and committing financial obligations.

Documented attack patterns abuse exactly the kind of access pod_create gives an agent:

POLICY

How to control pod_create

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_create:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "pod_create": {
      "deny_if": [
        {
          "conditions": [],
          "on_deny": "Requires human approval."
        }
      ]
    }
  }
}

Any call to pod_create is blocked until a human approves it. The rest of the server keeps working.

Create a free account and register Prime Intellect — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

GATE THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Prime Intellect tools

Financial pod_quote pod_quote Destructive pod_terminate pod_terminate Read get_wallet_balance Return the current Prime Intellect wallet balance and recent billings. Read list_availability list_availability Read list_gpu_types List every GPU type Prime Intellect currently offers (e.g. "H100_80GB", "A100_80GB"). Read pod_check_runaway Return locally-tracked pods that have run past max_lifetime_hours OR whose Read pod_list List every pod the API key can see (active + provisioning + stopped). Read pod_status pod_status

All 9 Prime Intellect tools →

Financial tools on other servers

0xarchive web3_subscribe Math MCP Server financial_calculator MCP Kling generate_video MCP Uber Server uber_request_ride

Go deeper

Critical-risk tools in Prime Intellect → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Human-in-the-loop → When a tool call should wait for a person — and when policy can decide alone.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
How to Add Spending Controls to Any MCP Agent →
Rate Limiting MCP Tool Calls: A Practical Guide →

FAQ

Questions about pod_create

What does the pod_create tool do? +

pod_create. It is categorised as a Financial tool in the Prime Intellect MCP Server, which means it involves financial transactions. Block by default and require explicit approval.

How do I enforce a policy on pod_create? +

Register the Prime Intellect MCP server in PolicyLayer and add a rule for pod_create: 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.

What risk level is pod_create? +

pod_create is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit pod_create? +

Yes. Add a rate_limit block to the pod_create 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 pod_create completely? +

Set action: deny in the PolicyLayer policy for pod_create. 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 pod_create? +

pod_create 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.

Enforce policy on every Prime Intellect tool call.

Start from Prime Intellect, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →