π ζ₯η Shizuku Watchdog θΏθ‘ηΆζγ
AI agents call watchdog_status to retrieve information from Android MCP Server without modifying anything β typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and displays the current status of the Shizuku Watchdog service. It performs a pure information query with no side effects, no data modification, no command execution, and no destructive operations. The emoji and description both indicate a monitoring/status-checking function typical of Read category tools.
From the tool's definition Tool description states 'ζ₯η Shizuku Watchdog θΏθ‘ηΆζ' (view/check Shizuku Watchdog running status). The verb 'ζ₯η' (view/check) indicates a read-only query operation that retrieves status information without modifying system state.
Attacks that exploit this kind of access
π ζ₯η Shizuku Watchdog θΏθ‘ηΆζγ. It is categorised as a Read tool in the Android MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Android MCP Server MCP server in PolicyLayer and add a rule for watchdog_status: 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.
watchdog_status is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the watchdog_status 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.
Set action: deny in the PolicyLayer policy for watchdog_status. 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.
watchdog_status 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →