Toggle mute/unmute for the current FaceTime call
AI agents invoke toggle_mute to trigger actions in macOS MCP Servers. 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 triggers an external operation on an active FaceTime call by toggling the mute state. It modifies the state of a live call (audio on/off), which is an external operation with real-time effects. It's not purely a data read/write, nor destructive or financial — it falls under Execute as it controls a running external application/process.
From the tool's definition Toggle mute/unmute for the current FaceTime call
Attacks that exploit this kind of access
Toggle mute/unmute for the current FaceTime call. It is categorised as a Execute tool in the macOS MCP Servers MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the macOS MCP Servers MCP server in PolicyLayer and add a rule for toggle_mute: 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 macOS MCP Servers. Nothing to install.
toggle_mute 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 toggle_mute 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 toggle_mute. 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.
toggle_mute is provided by the macOS MCP Servers MCP server (tdisawas0github/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 →