create_speech · Litellm MCP: Risk & Policy

WHAT IT DOES

What create_speech does on Litellm

AI agents invoke create_speech to trigger actions in Litellm. 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 create_speech needs a policy

This tool triggers an external AI/API operation (text-to-speech generation) that consumes compute resources and potentially incurs costs. It doesn't merely read data, but executes an audio generation process via an external service. It's not purely destructive or financial, but it does trigger an external operation whose effects (audio generation, API usage, potential cost) depend on input arguments.

From the tool's definition Generate speech audio from text using LiteLLM (/audio/speech)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_speech Rate-limited

create_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": {
    "create_speech": {
      "limits": [
        {
          "counter": "create_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 Litellm, so you can run agents against it safely.

FAQ

Questions about create_speech

What does the create_speech tool do? +

Generate speech audio from text using LiteLLM (/audio/speech). It is categorised as a Execute tool in the Litellm MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on create_speech? +

Register the Litellm MCP server in PolicyLayer and add a rule for create_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 Litellm. Nothing to install.

What risk level is create_speech? +

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

Can I rate-limit create_speech? +

Yes. Add a rate_limit block to the create_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 create_speech completely? +

Set action: deny in the PolicyLayer policy for create_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 create_speech? +

create_speech is provided by the Litellm MCP server (litellm-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.