Open a browser window for first-time Google login. Returns immediately
AI agents invoke setup_auth to trigger actions in Notebooklm. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a browser action (opens a browser window) to initiate a Google OAuth authentication flow. It triggers an external operation (browser launch and interaction with Google's login system) whose effects depend on the runtime environment. It is not a simple data read or write, but an execution of an external process/browser action.
From the tool's definition Open a browser window for first-time Google login. Returns immediately
Attacks that exploit this kind of access
Open a browser window for first-time Google login. Returns immediately. It is categorised as a Execute tool in the Notebooklm MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Notebooklm MCP server in PolicyLayer and add a rule for setup_auth: 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.
setup_auth is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the setup_auth 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 setup_auth. 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.
setup_auth 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 →