AI agents invoke play_music to trigger actions in Music. 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.
Playing music triggers an external operation on the system's audio output — it starts media playback, which is an action with real-world side effects (audio output, resource usage). This fits the Execute category as it triggers an external operation. Severity is medium since misuse could cause unwanted audio playback but has limited broader impact.
From the tool's definition Tool name 'play_music' and description '播放音乐' (play music), server description mentions 'playing songs with controls like play, pause, stop, and resume'
Attacks that exploit this kind of access
播放音乐. It is categorised as a Execute tool in the Music MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Music MCP server in PolicyLayer and add a rule for play_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 Music. Nothing to install.
play_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_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_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_music is provided by the Music MCP server (jxiufen/music-mcp-server). 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 →