select_device · Shotter MCP: Risk & Policy

WHAT IT DOES

What select_device does on Shotter

AI agents invoke select_device to trigger actions in Shotter. 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 select_device needs a policy

This tool triggers an external operation (booting an iOS Simulator and setting it as active), which is a side-effecting action that changes system state. It's not merely reading data, and it's not destructive or financial, but it does execute an operation on the host environment with real side effects.

From the tool's definition Boot an iOS simulator and set it as the active device

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

select_device Rate-limited

select_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": {
    "select_device": {
      "limits": [
        {
          "counter": "select_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 Shotter, so you can run agents against it safely.

FAQ

Questions about select_device

What does the select_device tool do? +

Boot an iOS simulator and set it as the active device. Uses fuzzy matching for device names. It is categorised as a Execute tool in the Shotter MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on select_device? +

Register the Shotter MCP server in PolicyLayer and add a rule for select_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 Shotter. Nothing to install.

What risk level is select_device? +

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

Can I rate-limit select_device? +

Yes. Add a rate_limit block to the select_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 select_device completely? +

Set action: deny in the PolicyLayer policy for select_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 select_device? +

select_device is provided by the Shotter MCP server (nathanstitt/shotter). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.