start_voice_capture · Pronunciation & Voice Coach MCP

WHAT IT DOES

What start_voice_capture does on Pronunciation & Voice Coach

AI agents invoke start_voice_capture to trigger actions in Pronunciation & Voice Coach. 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 start_voice_capture needs a policy

This tool executes a command to begin voice recording, which is an external operation with side effects (microphone state change, audio stream initiation). It does not retrieve data (Read), modify stored data reversibly (Write), or delete data (Destructive).

From the tool's definition Tool name 'start_voice_capture' indicates initiation of an audio recording operation. The empty description limits direct evidence, but the verb 'start' combined with 'voice_capture' suggests triggering an external hardware operation (microphone activation).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_voice_capture Rate-limited

start_voice_capture 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": {
    "start_voice_capture": {
      "limits": [
        {
          "counter": "start_voice_capture_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 Pronunciation & Voice Coach, so you can run agents against it safely.

FAQ

Questions about start_voice_capture

What does the start_voice_capture tool do? +

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

How do I enforce a policy on start_voice_capture? +

Register the Pronunciation & Voice Coach MCP server in PolicyLayer and add a rule for start_voice_capture: 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 Pronunciation & Voice Coach. Nothing to install.

What risk level is start_voice_capture? +

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

Can I rate-limit start_voice_capture? +

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

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

start_voice_capture is provided by the Pronunciation & Voice Coach MCP server (pypi:mcp-server-pronunciation). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.