AI agents use add_to_playlist to create or update resources in Xiaozhi — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Xiaozhi environment.
This tool creates or appends entries to a playlist, which is a reversible modification of data. It does not execute arbitrary code, delete data irreversibly, move money, or have destructive side effects. The change can be undone by removing the entry. Severity is low because the blast radius is limited to playlist state with no external system impact.
From the tool's definition Tool name 'add_to_playlist' and description '将歌曲添加到播放列表' (add song to playlist) indicates modification of a playlist data structure through creation/addition of entries.
Attacks that exploit this kind of access
将歌曲添加到播放列表。. It is categorised as a Write tool in the Xiaozhi MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Xiaozhi MCP server in PolicyLayer and add a rule for add_to_playlist: 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.
add_to_playlist is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_to_playlist 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 add_to_playlist. 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.
add_to_playlist 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 →