speak_and_confirm · Voice MCP: Risk & Policy

WHAT IT DOES

What speak_and_confirm does on Voice MCP

AI agents invoke speak_and_confirm 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_confirm needs a policy

This tool performs two chained external operations: it activates text-to-speech output via audio hardware and then captures microphone input for speech recognition. This goes beyond simple read/write of data — it triggers real-world audio I/O operations and captures user responses, which qualifies as Execute. Misuse could involve socially engineering a user via audio prompts and intercepting their spoken responses.

From the tool's definition 'Speak text aloud then immediately listen for a yes/no response' — combines output (TTS) and input (STT) operations, triggering external audio hardware and capturing user input

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

speak_and_confirm Rate-limited

speak_and_confirm 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_confirm": {
      "limits": [
        {
          "counter": "speak_and_confirm_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_confirm

What does the speak_and_confirm tool do? +

Speak text aloud then immediately listen for a yes/no 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_confirm? +

Register the Voice MCP server in PolicyLayer and add a rule for speak_and_confirm: 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_confirm? +

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

Can I rate-limit speak_and_confirm? +

Yes. Add a rate_limit block to the speak_and_confirm 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_confirm completely? +

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

speak_and_confirm 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.