watchdog_stop · Android MCP Server MCP: Risk & Policy

WHAT IT DOES

What watchdog_stop does on Android MCP Server

AI agents invoke watchdog_stop to trigger actions in Android MCP Server. 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 watchdog_stop needs a policy

Stopping a watchdog service is an Execute-category action because it runs/triggers an external operation (service termination) whose consequences are not fully reversible in real-time and could disrupt device monitoring/protection mechanisms. While not strictly destructive data deletion, it materially alters system state and could affect device stability or security.

From the tool's definition 'Stop Shizuku Watchdog' (watchdog_stop) terminates a system-level daemon service on an Android device. This is an execute operation that triggers external system operations with effects that depend on the device state and any processes relying on the watchdog…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

watchdog_stop Rate-limited

watchdog_stop 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": {
    "watchdog_stop": {
      "limits": [
        {
          "counter": "watchdog_stop_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 Android MCP Server, so you can run agents against it safely.

FAQ

Questions about watchdog_stop

What does the watchdog_stop tool do? +

⏹️ 停止 Shizuku Watchdog 守护。. It is categorised as a Execute tool in the Android MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on watchdog_stop? +

Register the Android MCP Server MCP server in PolicyLayer and add a rule for watchdog_stop: 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 Android MCP Server. Nothing to install.

What risk level is watchdog_stop? +

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

Can I rate-limit watchdog_stop? +

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

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

watchdog_stop is provided by the Android MCP Server MCP server (wujie272/android-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.