speak_text · Voiceroid Daemon MCP: Risk & Policy

WHAT IT DOES

What speak_text does on Voiceroid Daemon

AI agents invoke speak_text to trigger actions in Voiceroid Daemon. 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_text needs a policy

This tool executes an external text-to-speech process (VOICEROID2 via voiceroid_daemon) and plays audio through the system. It is not a simple read/write operation; it triggers external operations (audio synthesis and playback) whose effects depend on the input text. Misuse could involve generating and playing arbitrary audio content through the user's speakers.

From the tool's definition "Generate speech audio from text and play it" — triggers external audio synthesis and playback operations

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

speak_text Rate-limited

speak_text 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_text": {
      "limits": [
        {
          "counter": "speak_text_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 Voiceroid Daemon, so you can run agents against it safely.

FAQ

Questions about speak_text

What does the speak_text tool do? +

Generate speech audio from text and play it. It is categorised as a Execute tool in the Voiceroid Daemon 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_text? +

Register the Voiceroid Daemon MCP server in PolicyLayer and add a rule for speak_text: 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 Voiceroid Daemon. Nothing to install.

What risk level is speak_text? +

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

Can I rate-limit speak_text? +

Yes. Add a rate_limit block to the speak_text 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_text completely? +

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

speak_text is provided by the Voiceroid Daemon MCP server (mohemohe/voiceroid_daemon-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.