AI agents invoke play_web_music to trigger actions in xigua-MCP. 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 an external operation: it searches a music service (GD音乐台) and initiates playback. It is not merely reading/querying data; it triggers an active media session on the remote system, consistent with the Execute category. The blast radius is moderate — it can cause unwanted audio playback or interfere with the user's system state, but does not delete data or move money.
From the tool's definition '搜索并播放指定歌曲' — the tool searches for and plays music, triggering external media playback operations
Attacks that exploit this kind of access
在GD音乐台搜索并播放指定歌曲。. It is categorised as a Execute tool in the xigua-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the xigua- MCP server in PolicyLayer and add a rule for play_web_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 xigua-MCP. Nothing to install.
play_web_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 play_web_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 play_web_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.
play_web_music is provided by the xigua- MCP server (xiguaxiaome/xigua-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 →