clone_voice · ElevenLabs MCP: Risk & Policy

WHAT IT DOES

What clone_voice does on ElevenLabs

AI agents use clone_voice to create or update resources in ElevenLabs — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ElevenLabs environment.

WHY IT NEEDS A POLICY

Why clone_voice needs a policy

This tool creates a new voice clone resource in ElevenLabs from provided audio samples. It is a Write operation as it creates new data (a voice clone) on the platform. While voice cloning has potential misuse implications (deepfakes, impersonation), the tool itself is a reversible creation operation — the clone can presumably be deleted.

From the tool's definition 'Create an instant voice clone from audio samples'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

clone_voice Rate-limited

clone_voice stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "clone_voice": {
      "limits": [
        {
          "counter": "clone_voice_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 clone_voice

What does the clone_voice tool do? +

Create an instant voice clone from audio samples. Requires 1-2 minutes of clear audio. Trigger:. It is categorised as a Write tool in the ElevenLabs MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on clone_voice? +

Register the ElevenLabs MCP server in PolicyLayer and add a rule for clone_voice: 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 clone_voice? +

clone_voice is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit clone_voice? +

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

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

clone_voice 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.