The NotebookLM MCP Server provides a secure environment for querying and managing NotebookLM notebooks, enabling programmatic creation and management of notebooks, audio and video overviews, and data extraction.
From the registry: Security-hardened NotebookLM MCP with post-quantum encryption
Please install the `notebooklm-mcp-secure` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js** — Node.js runtime required for npx (https://nodejs.org/)
- **Google NotebookLM account** — Requires a dedicated Google account for browser automation (https://notebooklm.google.com/)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@pan-sec/notebooklm-mcp@latest"]
- optional environment variables:
- `NLMCP_AUTH_ENABLED`: Enable auth token guard (example: `true`)
- `NLMCP_AUTH_TOKEN`: Auth token (generate with `openssl rand -base64 32`) (example: `<your-auth-token>`)
- `GEMINI_API_KEY`: Optional Gemini API key for deep_research, gemini_query, upload_document features (example: `<your-gemini-api-key>`)
Note: Security-hardened fork of notebooklm-mcp with constant-time auth and MCP SDK 1.26.0. Gemini API key unlocks advanced features.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AI-powered threat hunting and incident response MCP server for Elasticsearch/OpenSearch