tts_stop · Tts MCP: Risk & Policy

WHAT IT DOES

What tts_stop does on Tts

AI agents invoke tts_stop to trigger actions in Tts. 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 tts_stop needs a policy

This tool executes a command to control an external audio player rather than simply reading or writing data. While the action is reversible (audio can be replayed) and relatively benign, it fits the Execute category because it triggers an external operation with side effects. The blast radius is minimal (only affects current audio playback), making severity low.

From the tool's definition Tool name 'tts_stop' and description 'Stop currently playing audio started by the configured player' indicate an action that triggers an external operation (stopping audio playback) whose effects depend on the current state of the player.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tts_stop Rate-limited

tts_stop 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": {
    "tts_stop": {
      "limits": [
        {
          "counter": "tts_stop_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 Tts, so you can run agents against it safely.

FAQ

Questions about tts_stop

What does the tts_stop tool do? +

Stop currently playing audio started by the configured player. It is categorised as a Execute tool in the Tts MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on tts_stop? +

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

What risk level is tts_stop? +

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

Can I rate-limit tts_stop? +

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

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

tts_stop is provided by the Tts MCP server (that-lucas/tts-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.