Two-phase deep cleanup of all server data on disk (auth state,
AI agents call cleanup_data to permanently remove resources in Notebooklm — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs a deep cleanup of all server data on disk, including authentication state. 'Deep cleanup of all server data' implies irreversible deletion of persistent data. The scope is sweeping (all data), making misuse catastrophic with no recovery path — hence critical severity.
From the tool's definition 'Two-phase deep cleanup of all server data on disk (auth state'
Attacks that exploit this kind of access
Two-phase deep cleanup of all server data on disk (auth state,. It is categorised as a Destructive tool in the Notebooklm MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Notebooklm MCP server in PolicyLayer and add a rule for cleanup_data: 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.
cleanup_data is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the cleanup_data 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 cleanup_data. 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.
cleanup_data 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 →