Save the completed Audio Overview to disk as a
AI agents use download_audio to create or update resources in Notebooklm — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Notebooklm environment.
This tool saves/downloads audio content to disk, which is a write operation to the local filesystem. The description appears to be truncated ('as a'), reducing confidence slightly. The blast radius is medium as it writes files to disk but does not delete or modify existing data, and has no financial implications.
From the tool's definition 'Save the completed Audio Overview to disk' — writes a file to the local filesystem
Attacks that exploit this kind of access
Save the completed Audio Overview to disk as a. It is categorised as a Write tool in the Notebooklm MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Notebooklm MCP server in PolicyLayer and add a rule for download_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.
download_audio is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the download_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.
Set action: deny in the PolicyLayer policy for download_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.
download_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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →