stop_gpu_instance · Nebulablock MCP: Risk & Policy

WHAT IT DOES

What stop_gpu_instance does on Nebulablock

AI agents invoke stop_gpu_instance to trigger actions in Nebulablock. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why stop_gpu_instance needs a policy

Stopping a GPU instance is an Execute action because it triggers an external operation (halting a running compute resource) whose effects depend on the arguments provided (which instance to stop). While reversible (unlike Destructive), it modifies the operational state of infrastructure and could disrupt workloads.

From the tool's definition Tool name 'stop_gpu_instance' indicates operational control over compute infrastructure. Related tools on the same server include create_gpu_instance and delete_gpu_instance, establishing this as an infrastructure management API.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_gpu_instance Rate-limited

stop_gpu_instance stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "stop_gpu_instance": {
      "limits": [
        {
          "counter": "stop_gpu_instance_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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 stop_gpu_instance

What does the stop_gpu_instance tool do? +

stop_gpu_instance. It is categorised as a Execute tool in the Nebulablock MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on stop_gpu_instance? +

Register the Nebulablock MCP server in PolicyLayer and add a rule for stop_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 stop_gpu_instance? +

stop_gpu_instance is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit stop_gpu_instance? +

Yes. Add a rate_limit block to the stop_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 stop_gpu_instance completely? +

Set action: deny in the PolicyLayer policy for stop_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 stop_gpu_instance? +

stop_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.