watchdog_start · Android MCP Server MCP: Risk & Policy

WHAT IT DOES

What watchdog_start does on Android MCP Server

AI agents invoke watchdog_start 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_start needs a policy

This tool executes a daemon process that modifies system behavior—specifically, it creates a watchdog that monitors and automatically restarts another service. This is a form of code execution that triggers external operations with side effects that depend on system state and configuration.

From the tool's definition Tool starts a Shizuku Watchdog daemon that automatically relaunches MCP if Termux is killed. The description explicitly states '启动 Shizuku Watchdog 守护' (starts Shizuku Watchdog daemon) and '自动拉起 MCP' (automatically pulls up MCP).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

watchdog_start Rate-limited

watchdog_start 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_start": {
      "limits": [
        {
          "counter": "watchdog_start_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_start

What does the watchdog_start tool do? +

🛡️ 启动 Shizuku Watchdog 守护（Termux 被杀后自动拉起 MCP）。. 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_start? +

Register the Android MCP Server MCP server in PolicyLayer and add a rule for watchdog_start: 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_start? +

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

Can I rate-limit watchdog_start? +

Yes. Add a rate_limit block to the watchdog_start 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_start completely? +

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

watchdog_start 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.