create-endpoint · RunPod MCP Server MCP: Risk & Policy

WHAT IT DOES

What create-endpoint does on RunPod MCP Server

AI agents use create-endpoint 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.

WHY IT NEEDS A POLICY

Why create-endpoint needs a policy

Creating an endpoint in RunPod instantiates a new inference endpoint, which is a resource that can serve models and incur compute costs. This is a reversible write operation (the endpoint can be deleted via delete-endpoint), not destructive. However, it has high severity because an AI agent creating arbitrary endpoints could lead to resource consumption, cost impact, and unauthorized service exposure.

From the tool's definition Tool name is 'create-endpoint' which indicates creation of a new endpoint resource in the RunPod system. Sibling tools like 'delete-endpoint' and other 'create-*' operations confirm this is a write operation that modifies RunPod infrastructure.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create-endpoint Rate-limited

create-endpoint 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create-endpoint": {
      "limits": [
        {
          "counter": "create-endpoint_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 create-endpoint

What does the create-endpoint tool do? +

create-endpoint. 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.

How do I enforce a policy on create-endpoint? +

Register the RunPod MCP Server MCP server in PolicyLayer and add a rule for create-endpoint: 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 create-endpoint? +

create-endpoint is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create-endpoint? +

Yes. Add a rate_limit block to the create-endpoint 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 create-endpoint completely? +

Set action: deny in the PolicyLayer policy for create-endpoint. 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 create-endpoint? +

create-endpoint 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.