text_to_speech · ElevenLabs MCP: Risk & Policy

WHAT IT DOES

What text_to_speech does on ElevenLabs

AI agents invoke text_to_speech to trigger actions in ElevenLabs. 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 text_to_speech needs a policy

While the tool itself is not destructive or financial, it executes an external operation (audio generation via ElevenLabs API) rather than simply retrieving data. The tool produces side effects (audio file generation, API calls, potential resource consumption/billing) and its behavior is contingent on user-supplied arguments. This fits the Execute category—an operation that runs external code/service calls.

From the tool's definition The tool 'text_to_speech' converts text to natural speech using ElevenLabs, which triggers an external API operation that generates audio output based on provided arguments (text input and voice parameters).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

text_to_speech Rate-limited

text_to_speech 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": {
    "text_to_speech": {
      "limits": [
        {
          "counter": "text_to_speech_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 ElevenLabs, so you can run agents against it safely.

FAQ

Questions about text_to_speech

What does the text_to_speech tool do? +

Convert text to natural speech using ElevenLabs. It is categorised as a Execute tool in the ElevenLabs MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on text_to_speech? +

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

What risk level is text_to_speech? +

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

Can I rate-limit text_to_speech? +

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

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

text_to_speech is provided by the ElevenLabs MCP server (wynandw87/claude-code-elevenlabs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.