speak · Voice Bridge MCP: Risk & Policy

WHAT IT DOES

What speak does on Voice Bridge

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

This tool executes an action on the host system (producing audio output), which constitutes an external side-effect beyond simple data read/write. An AI agent could misuse it to produce unwanted or disruptive audio output. It falls under Execute as it triggers an external operation whose effects depend on the input text argument.

From the tool's definition "Speak text aloud" — triggers an external audio output operation on the host system using a TTS engine

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

speak Rate-limited

speak 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": {
      "limits": [
        {
          "counter": "speak_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 Bridge, so you can run agents against it safely.

FAQ

Questions about speak

What does the speak tool do? +

Speak text aloud using the configured TTS engine. It is categorised as a Execute tool in the Voice Bridge 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? +

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

What risk level is speak? +

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

Can I rate-limit speak? +

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

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

speak is provided by the Voice Bridge MCP server (Tomorrow-You/voice-bridge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.