generate_audio · Notebooklm MCP: Risk & Policy

WHAT IT DOES

What generate_audio does on Notebooklm

AI agents invoke generate_audio to trigger actions in Notebooklm. 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 generate_audio needs a policy

This tool triggers an external operation (audio generation) on a remote service. It initiates a generation process whose effects depend on the notebook's content. It is not a simple read, and it creates a new artifact (audio), making it at minimum a Write, but 'trigger' and the generative/execution nature of the operation place it in Execute. Misuse could consume resources or generate unwanted audio content at scale.

From the tool's definition "Trigger podcast-style Audio Overview generation for a notebook"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_audio Rate-limited

generate_audio 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": {
    "generate_audio": {
      "limits": [
        {
          "counter": "generate_audio_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 Notebooklm, so you can run agents against it safely.

FAQ

Questions about generate_audio

What does the generate_audio tool do? +

Trigger podcast-style Audio Overview generation for a notebook.\n\n. It is categorised as a Execute tool in the Notebooklm MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on generate_audio? +

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

What risk level is generate_audio? +

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

Can I rate-limit generate_audio? +

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

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

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