Medium Risk

create-gpu-instance

create-gpu-instance

How to control create-gpu-instance ↓

What create-gpu-instance does on Novita MCP Server

AI agents use create-gpu-instance to create or update resources in Novita MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Novita MCP Server environment.

Medium Risk

Why create-gpu-instance needs a policy

Based on the tool name and server context, this tool creates a GPU instance on the Novita AI platform. Creating cloud compute resources is a Write operation with high severity due to potential cost implications and resource provisioning at scale. While it could have financial implications, it is primarily a resource creation (Write) action rather than a direct financial transaction.

From the tool's definition Tool name 'create-gpu-instance'; server description mentions 'create' as one of the GPU instance operations. Description is empty/uninformative.

Documented attack patterns abuse exactly the kind of access create-gpu-instance gives an agent:

How to control create-gpu-instance

PolicyLayer is an MCP gateway — it sits between your AI agents and Novita MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create-gpu-instance:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create-gpu-instance": {
      "limits": [
        {
          "counter": "create-gpu-instance_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

create-gpu-instance 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.

  1. Create a free account and register Novita MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about create-gpu-instance

What does the create-gpu-instance tool do? +

create-gpu-instance. It is categorised as a Write tool in the Novita 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-gpu-instance? +

Register the Novita MCP Server MCP server in PolicyLayer and add a rule for create-gpu-instance: 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 Novita MCP Server. Nothing to install.

What risk level is create-gpu-instance? +

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

Can I rate-limit create-gpu-instance? +

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

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

create-gpu-instance is provided by the Novita MCP Server MCP server (novitalabs/novita-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Novita MCP Server tool call.

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

Free to start. No card required.

20 Novita MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.