Set a notebook as the active default (used when ask_question has no notebook_id). When To Use - User switches context:
AI agents use select_notebook to create or update resources in NotebookLM MCP Structured — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your NotebookLM MCP Structured environment.
The tool modifies application state by selecting/updating the active notebook context. This is a Write operation: it creates or modifies data (the active notebook selection) reversibly. It has no destructive effects, doesn't execute external code, and doesn't involve financial transactions.
From the tool's definition 'Set a notebook as the active default' indicates state modification of which notebook is the current context. This is a reversible preference/configuration change.
Documented attack patterns abuse exactly the kind of access select_notebook gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and NotebookLM MCP Structured, and nothing reaches the server without passing your rules. This is the rule we recommend for select_notebook:
{
"version": "1",
"default": "deny",
"tools": {
"select_notebook": {
"limits": [
{
"counter": "select_notebook_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}select_notebook 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.
Free to start. No card required.
Set a notebook as the active default (used when ask_question has no notebook_id). When To Use - User switches context:. It is categorised as a Write tool in the NotebookLM MCP Structured MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the NotebookLM MCP Structured MCP server in PolicyLayer and add a rule for select_notebook: 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 MCP Structured. Nothing to install.
select_notebook 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 select_notebook 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 select_notebook. 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.
select_notebook is provided by the NotebookLM MCP Structured MCP server (paolodalprato/notebooklm-mcp-structured). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 15 NotebookLM MCP Structured tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
15 NotebookLM MCP Structured tools catalogued and risk-classified — across an index of 42,500+ MCP servers.