create_gpu_instance · Nebulablock MCP: Risk & Policy

WHAT IT DOES

What create_gpu_instance does on Nebulablock

AI agents use create_gpu_instance to create or update resources in Nebulablock — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nebulablock environment.

WHY IT NEEDS A POLICY

Why create_gpu_instance needs a policy

Creating a GPU instance provisions cloud compute resources, which incurs costs and creates infrastructure. This is a Write action (reversible via deletion). However, since it involves resource provisioning that likely has financial implications, severity is high.

From the tool's definition Tool name 'create_gpu_instance' — sibling tools include 'delete_gpu_instance', 'get_computing_products', suggesting this creates a cloud GPU instance. Description is empty.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_gpu_instance Rate-limited

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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_gpu_instance": {
      "limits": [
        {
          "counter": "create_gpu_instance_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 Nebulablock, so you can run agents against it safely.

FAQ

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 Nebulablock 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 Nebulablock 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 Nebulablock. 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 Nebulablock MCP server (nebula-block-data/nebulablock-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.