Play an error system sound
AI agents invoke play_error_sound to trigger actions in MCP Make Sound. 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 a system-level audio playback operation. It causes a side effect (playing a sound) on the host macOS system. While the blast radius is minimal (only produces an audible sound with no data modification or financial impact), it does trigger an external operation, placing it in the Execute category. Severity is low as misuse is largely harmless.
From the tool's definition "Play an error system sound" - triggers an external audio operation on the host system
Attacks that exploit this kind of access
Play an error system sound. It is categorised as a Execute tool in the MCP Make Sound MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Make Sound MCP server in PolicyLayer and add a rule for play_error_sound: 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 MCP Make Sound. Nothing to install.
play_error_sound 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_error_sound 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_error_sound. 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_error_sound is provided by the MCP Make Sound MCP server (nocoo/mcp-make-sound). 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 →