The `notebooklm-mcp-server` package, currently at version 3.0.7, provides a robust Node.js-based server that enables AI agents to interact directly with Google's NotebookLM. Built with TypeScript and leveraging the Model Context Protocol (MCP), this server allows AI agents to securely read, search, and manage NotebookLM notebooks as if they were local files. This direct integration is designed to provide grounded context to AI models, significantly reducing hallucinations. It supports both global installation via npm and zero-configuration execution via npx, making it highly accessible for integration into various AI-augmented workflows. The project maintains an active release cadence, featuring an auto-update mechanism that ensures the server always runs the latest version with critical fixes and enhancements upon startup. Its core differentiation lies in offering a dedicated, protocol-driven solution for real-time context retrieval directly from NotebookLM for AI applications.
npm install notebooklm-mcp-serverVerified import paths — ran on the pinned version, not inferred.
Demonstrates the essential steps to authenticate with Google NotebookLM and then start the MCP server using npx.
After an auto-update notification, manually restart the server process to use the newly installed version.
Re-run the authentication command: `npx notebooklm-mcp-server auth`. A browser window will open for re-login. After successful login, close the browser.
Upgrade your Node.js installation to version 18.0.0 or newer. Use a version manager like `nvm` to easily switch Node.js versions (`nvm install 18 && nvm use 18`).
Run `npx notebooklm-mcp-server auth` and follow the browser prompts to log in to your Google account again.
Ensure your project uses ES Modules (add `"type": "module"` to `package.json`) or use dynamic `import()` for ESM-only dependencies. The primary intended usage is via `npx`, which handles module resolution.
No dependency data recorded yet.