AI agents call resolve_music_url to retrieve information from Xiaozhi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool resolves/fetches a music URL without triggering playback or modifying any data. It is a pure read/lookup operation that retrieves a direct link to a song resource. No side effects are described.
From the tool's definition 解析歌曲最终直链，不直接播放 (Resolves the final direct link of a song, does not play directly)
Attacks that exploit this kind of access
解析歌曲最终直链，不直接播放。兼容 id/song_id 两种参数命名。. It is categorised as a Read tool in the Xiaozhi MCP Server, which means it retrieves data without modifying state.
Register the Xiaozhi MCP server in PolicyLayer and add a rule for resolve_music_url: 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.
resolve_music_url 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 resolve_music_url 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 resolve_music_url. 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.
resolve_music_url 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 →