AI agents invoke previous_song 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 triggers an external operation — changing the currently playing track in a music player. It does not read, write, or delete data, but executes a playback control action whose effect depends on the current playlist state.
From the tool's definition 切换到播放列表中的上一首歌 (Switch to the previous song in the playlist)
Attacks that exploit this kind of access
切换到播放列表中的上一首歌。. 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 previous_song: 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.
previous_song 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 previous_song 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 previous_song. 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.
previous_song 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 →