Search the library by free-text query — matches against
AI agents call search_notebooks to retrieve information from Notebooklm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or searches data without side effects. It queries the notebook library and returns matching results, which is characteristic of Read operations. The incomplete description ('matches against') doesn't suggest any destructive or executable capabilities. The blast radius of misuse is minimal—an AI agent could only retrieve information an authenticated user already has access to.
From the tool's definition Tool name 'search_notebooks' and description indicate a free-text search/query operation that 'matches against' notebook content. No modification, deletion, execution, or financial operations are described.
Attacks that exploit this kind of access
Search the library by free-text query — matches against. It is categorised as a Read tool in the Notebooklm MCP Server, which means it retrieves data without modifying state.
Register the Notebooklm 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. 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 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 →