set_device · Phantom MCP: Risk & Policy

WHAT IT DOES

What set_device does on Phantom

AI agents invoke set_device to trigger actions in Phantom. 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 set_device needs a policy

Setting and potentially starting a device is an external operation with side effects (spinning up a simulator/emulator). It goes beyond a simple read but doesn't destructively delete or modify persistent data, placing it in Execute category. Misuse could cause unintended device startup or session hijacking, warranting medium severity.

From the tool's definition 'Sélectionne le device à utiliser pour cette session de test. Si le device est éteint, il sera démarré automatiquement' — the tool selects a device and can automatically start/power on a device (simulator/emulator), triggering an external operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

set_device Rate-limited

set_device 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": {
    "set_device": {
      "limits": [
        {
          "counter": "set_device_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 Phantom, so you can run agents against it safely.

FAQ

Questions about set_device

What does the set_device tool do? +

Sélectionne le device à utiliser pour cette session de test. Si le device est éteint, il sera démarré automatiquement. Appelle list_devices d. It is categorised as a Execute tool in the Phantom MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on set_device? +

Register the Phantom MCP server in PolicyLayer and add a rule for set_device: 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 Phantom. Nothing to install.

What risk level is set_device? +

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

Can I rate-limit set_device? +

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

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

set_device is provided by the Phantom MCP server (nthimpulse/phantom-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.