AI agents invoke stop_music to trigger actions in Xiaozhi. 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.
This tool executes a command that controls media playback state—stopping playback and clearing the current track. While the action is reversible (playback can be resumed), it represents execution of an external operation whose effects depend on system state. It does not retrieve data (Read), create/modify persistent data (Write), irreversibly delete data (Destructive), or involve financial transactions (Financial).
From the tool's definition Tool name 'stop_music' and description '停止音乐播放并清除当前曲目' (stop music playback and clear current track) indicate it triggers an external operation on a music player/media system.
Attacks that exploit this kind of access
停止音乐播放并清除当前曲目。. It is categorised as a Execute tool in the Xiaozhi MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Xiaozhi MCP server in PolicyLayer and add a rule for stop_music: 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 Xiaozhi. Nothing to install.
stop_music is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the stop_music 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 stop_music. 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.
stop_music is provided by the Xiaozhi MCP server (zhouhaojiang/xiaozhi-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 →