end_current_call · macOS MCP Servers MCP: Risk & Policy

WHAT IT DOES

What end_current_call does on macOS MCP Servers

AI agents invoke end_current_call 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.

WHY IT NEEDS A POLICY

Why end_current_call needs a policy

Terminating an active FaceTime call is an external operation with immediate real-world consequences (abruptly ending a live communication session). It triggers an action on a native macOS application and cannot be undone once executed. This fits Execute as it triggers an external operation, with high severity since misuse would abruptly terminate someone's active call without consent.

From the tool's definition End the current FaceTime call

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

end_current_call Rate-limited

end_current_call stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "end_current_call": {
      "limits": [
        {
          "counter": "end_current_call_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches macOS MCP Servers, so you can run agents against it safely.

FAQ

Questions about end_current_call

What does the end_current_call tool do? +

End 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.

How do I enforce a policy on end_current_call? +

Register the macOS MCP Servers MCP server in PolicyLayer and add a rule for end_current_call: 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.

What risk level is end_current_call? +

end_current_call is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit end_current_call? +

Yes. Add a rate_limit block to the end_current_call 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.

How do I block end_current_call completely? +

Set action: deny in the PolicyLayer policy for end_current_call. 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.

What MCP server provides end_current_call? +

end_current_call 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.