Permanently close a session and discard its browser tab. Use the
AI agents call close_session 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 irreversibly closes and discards a session, preventing any recovery of session data or continuation of work. While not directly deleting user content, it permanently destroys an active session context. This qualifies as Destructive rather than Write because the action cannot be undone and involves discard/removal semantics.
From the tool's definition Tool description states 'Permanently close a session and discard its browser tab' — 'permanently' indicates an irreversible action that discards/removes session state.
Attacks that exploit this kind of access
Permanently close a session and discard its browser tab. Use the. 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 close_session: 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.
close_session 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 close_session 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 close_session. 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.
close_session 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 →