generate_speech · Media MCP: Risk & Policy

WHAT IT DOES

What generate_speech does on Media

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

WHY IT NEEDS A POLICY

Why generate_speech needs a policy

This tool creates a new audio artifact (speech) from text input. It is a Write operation because it generates and likely stores or returns a new media file. There are no destructive, financial, or code-execution implications. Severity is medium because misuse could generate misleading or harmful audio content (e.g., voice cloning-style speech), though the blast radius is limited compared to video or financial tools.

From the tool's definition Generate speech audio from text using Gemini TTS models

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_speech Rate-limited

generate_speech 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": {
    "generate_speech": {
      "limits": [
        {
          "counter": "generate_speech_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 Media, so you can run agents against it safely.

FAQ

Questions about generate_speech

What does the generate_speech tool do? +

Generate speech audio from text using Gemini TTS models. It is categorised as a Write tool in the Media MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on generate_speech? +

Register the Media MCP server in PolicyLayer and add a rule for generate_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 Media. Nothing to install.

What risk level is generate_speech? +

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

Can I rate-limit generate_speech? +

Yes. Add a rate_limit block to the generate_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 generate_speech completely? +

Set action: deny in the PolicyLayer policy for generate_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 generate_speech? +

generate_speech is provided by the Media MCP server (lukaskellerstein/media-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.