save_audio · Edge-TTS MCP Server MCP: Risk & Policy

WHAT IT DOES

What save_audio does on Edge-TTS MCP Server

AI agents use save_audio to create or update resources in Edge-TTS MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Edge-TTS MCP Server environment.

WHY IT NEEDS A POLICY

Why save_audio needs a policy

This tool creates or modifies audio files (a form of data creation), which fits the Write category. It is reversible—generated audio files can be deleted or overwritten. Severity is low because saving audio has minimal blast radius; the worst outcome is storage of unwanted audio files, which is not destructive, financial, or code-execution.

From the tool's definition Tool name 'save_audio' indicates writing/persisting audio data. Server context shows it generates audio files from text-to-speech synthesis. The sibling tool 'text_to_speech' and server capability to 'generate audio files' confirms this writes new media files.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_audio Rate-limited

save_audio 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": {
    "save_audio": {
      "limits": [
        {
          "counter": "save_audio_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 Edge-TTS MCP Server, so you can run agents against it safely.

FAQ

Questions about save_audio

What does the save_audio tool do? +

save_audio. It is categorised as a Write tool in the Edge-TTS MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_audio? +

Register the Edge-TTS MCP Server MCP server in PolicyLayer and add a rule for save_audio: 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 Edge-TTS MCP Server. Nothing to install.

What risk level is save_audio? +

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

Can I rate-limit save_audio? +

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

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

save_audio is provided by the Edge-TTS MCP Server MCP server (yangwuan55/edge-tts-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.