Ask the active NotebookLM notebook a question.
AI agents call notebooklm_ask to retrieve information from Notebooklm Codex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves answers to questions from a notebook, which is a read-only operation with no side effects on data creation, modification, or deletion. The worst-case misuse would be querying sensitive information that the notebook contains, but this is bounded by the notebook's existing content and access controls. Severity is low because the tool cannot create, modify, delete, execute code, or move funds.
From the tool's definition Tool description states 'Ask the active NotebookLM notebook a question' — this is a query operation that retrieves information from an existing notebook without modifying it.
Attacks that exploit this kind of access
Ask the active NotebookLM notebook a question. It is categorised as a Read tool in the Notebooklm Codex MCP Server, which means it retrieves data without modifying state.
Register the Notebooklm Codex MCP server in PolicyLayer and add a rule for notebooklm_ask: 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 Codex. Nothing to install.
notebooklm_ask 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 notebooklm_ask 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 notebooklm_ask. 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.
notebooklm_ask is provided by the Notebooklm Codex MCP server (knowingdoing/notebooklm-codex). 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 →