Search library by query (name, description, topics, tags).
AI agents call search_notebooks to retrieve information from NotebookLM MCP Structured without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data without side effects. It searches notebook metadata to find matching results, which is a classic Read operation. The restricted scope (library metadata only) and query-based nature present minimal security risk even if misused by an AI agent.
From the tool's definition Tool name 'search_notebooks' and description explicitly states it 'Search[es] library by query' across metadata fields (name, description, topics, tags). No modification, deletion, or execution capabilities are present.
Documented attack patterns abuse exactly the kind of access search_notebooks 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 search_notebooks:
{
"version": "1",
"default": "deny",
"tools": {
"search_notebooks": {}
}
}search_notebooks is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search library by query (name, description, topics, tags). It is categorised as a Read tool in the NotebookLM MCP Structured MCP Server, which means it retrieves data without modifying state.
Register the NotebookLM MCP Structured MCP server in PolicyLayer and add a rule for search_notebooks: 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.
search_notebooks is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_notebooks 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 search_notebooks. 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.
search_notebooks 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.