speak_and_listen · Voice MCP: Risk & Policy

WHAT IT DOES

What speak_and_listen does on Voice MCP

AI agents invoke speak_and_listen to trigger actions in Voice 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.

WHY IT NEEDS A POLICY

Why speak_and_listen needs a policy

This tool both produces audio output and captures audio input in sequence, triggering external hardware operations (speaker and microphone). It goes beyond a simple read or write, as it executes a multi-step interaction with external systems (local Whisper STT and Supertonic TTS).

From the tool's definition 'Speak text aloud then immediately listen for a full response' — triggers both audio output (TTS) and audio input (STT) operations as a combined external interaction

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

speak_and_listen Rate-limited

speak_and_listen 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": {
    "speak_and_listen": {
      "limits": [
        {
          "counter": "speak_and_listen_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 Voice MCP, so you can run agents against it safely.

FAQ

Questions about speak_and_listen

What does the speak_and_listen tool do? +

Speak text aloud then immediately listen for a full response. It is categorised as a Execute tool in the Voice MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on speak_and_listen? +

Register the Voice MCP server in PolicyLayer and add a rule for speak_and_listen: 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 Voice MCP. Nothing to install.

What risk level is speak_and_listen? +

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

Can I rate-limit speak_and_listen? +

Yes. Add a rate_limit block to the speak_and_listen 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 speak_and_listen completely? +

Set action: deny in the PolicyLayer policy for speak_and_listen. 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 speak_and_listen? +

speak_and_listen is provided by the Voice MCP server (jochiang/voice-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.