voice_converse · Voice MCP: Risk & Policy

WHAT IT DOES

What voice_converse does on Voice

AI agents invoke voice_converse to trigger actions in Voice. 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 voice_converse needs a policy

The server is designed to allow LLMs to speak and listen via bidirectional voice loops. A tool named 'voice_converse' most likely triggers real-time audio input/output operations — an external operation that executes a voice interaction loop. This falls under Execute due to triggering external audio I/O operations. Confidence is reduced due to the empty description.

From the tool's definition Tool name 'voice_converse' on a server described as enabling 'bidirectional voice loops' for speaking and listening; description is empty.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

voice_converse Rate-limited

voice_converse 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": {
    "voice_converse": {
      "limits": [
        {
          "counter": "voice_converse_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, so you can run agents against it safely.

FAQ

Questions about voice_converse

What does the voice_converse tool do? +

voice_converse. It is categorised as a Execute tool in the Voice MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on voice_converse? +

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

What risk level is voice_converse? +

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

Can I rate-limit voice_converse? +

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

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

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