NotebookLM
Enables AI agents to interact with Google NotebookLM and Gemini API for document analysis, deep research, and notebook creation with enterprise-grade security including post-quantum encryption and 14 security layers.
What is NotebookLM?
NotebookLM is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables ai agents to interact with google notebooklm and gemini api for document analysis, deep research, and notebook creation with enterprise-grade security including post-quantum encryption and 14 ...
Enables AI agents to interact with Google NotebookLM and Gemini API for document analysis, deep research, and notebook creation with enterprise-grade security including post-quantum encryption and 14 security layers.
This server falls under the Browser Automation category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables AI agents to interact with Google NotebookLM and Gem
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @pan-sec/notebooklm-mcpManual Installation
npx -y @pan-sec/notebooklm-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use NotebookLM
The NotebookLM MCP Server (Security Hardened) by Pantheon Security enables AI agents to programmatically interact with Google NotebookLM and the Gemini API for automated document analysis, deep research, notebook creation, and audio/video overview generation. It provides 33 standard tools — covering notebook management, structured data extraction, session handling, and deep research synthesis — with an optional Gemini API integration that unlocks multi-source research, PDF upload, and web-grounded queries. The server implements enterprise-grade security including post-quantum encryption and audit logging.
Prerequisites
- Node.js 18 or later installed on your system
- A Google account with access to NotebookLM (notebooklm.google.com)
- A Google Gemini API key (optional, for deep research and PDF upload features — obtainable free at aistudio.google.com)
- An MCP-compatible client such as Claude Desktop or Claude Code
Add the server to Claude Code via CLI
The fastest setup uses the Claude Code CLI to add the server. For basic use without Gemini, no API key is required.
claude mcp add notebooklm -- npx @pan-sec/notebooklm-mcp@latestOr add with authentication and Gemini enabled
For production use, enable authentication and supply your Gemini API key. The openssl command generates a random secure token.
claude mcp add notebooklm \
--env NLMCP_AUTH_ENABLED=true \
--env NLMCP_AUTH_TOKEN=$(openssl rand -base64 32) \
--env GEMINI_API_KEY=your-gemini-api-key \
-- npx @pan-sec/notebooklm-mcp@latestConfigure Claude Desktop (alternative)
Add the server manually to your claude_desktop_config.json if you prefer the Desktop app over Claude Code CLI.
{
"mcpServers": {
"notebooklm": {
"command": "npx",
"args": ["-y", "@pan-sec/notebooklm-mcp"],
"env": {
"NLMCP_AUTH_ENABLED": "true",
"NLMCP_AUTH_TOKEN": "your-generated-token",
"GEMINI_API_KEY": "your-gemini-api-key",
"GEMINI_DEFAULT_MODEL": "gemini-3-flash-preview"
}
}
}
}Authenticate with Google NotebookLM
On first use, tell Claude to log in to NotebookLM. The server will open Chrome and walk you through Google authentication. Your session is then stored for subsequent requests.
Create your first notebook
Once authenticated, you can create notebooks, add sources by URL, and start querying them. The server handles all browser automation transparently.
NotebookLM Examples
Client configuration
Claude Desktop config for the NotebookLM MCP server with authentication and Gemini API enabled.
{
"mcpServers": {
"notebooklm": {
"command": "npx",
"args": ["-y", "@pan-sec/notebooklm-mcp"],
"env": {
"NLMCP_AUTH_ENABLED": "true",
"NLMCP_AUTH_TOKEN": "your-secure-random-token",
"GEMINI_API_KEY": "AIza...",
"GEMINI_DEFAULT_MODEL": "gemini-3-flash-preview",
"NOTEBOOKLM_PROFILE": "standard",
"NLMCP_SESSION_MAX_LIFETIME": "28800"
}
}
}
}Prompts to try
Example tasks you can ask Claude to perform using the NotebookLM MCP server.
- "Log me in to NotebookLM"
- "Create a new NotebookLM notebook from these URLs: [list of URLs]"
- "Query my notebook about the main findings in the uploaded documents"
- "Use deep_research to synthesize what experts say about quantum computing timelines"
- "Generate an audio overview of my notebook in kawaii presentation style"
- "Extract all data tables from my notebook as structured JSON"Troubleshooting NotebookLM
Chrome does not open during authentication or browser automation fails
The server requires a visible Chrome or Chromium installation. Ensure Chrome is installed and not running in headless-only mode. If running on a server without a display, you need a virtual display (xvfb) or a desktop environment.
Gemini API features are not available after setting the key
Verify GEMINI_API_KEY is correctly set in the env block and that the key is active at aistudio.google.com. Check that NOTEBOOKLM_PROFILE is set to 'standard' or higher, as the 'minimal' profile disables advanced tools.
Session expires mid-conversation
By default sessions last 8 hours (NLMCP_SESSION_MAX_LIFETIME=28800). Increase this value in your config for longer working sessions, or tell Claude to log in again when the session expires.
Frequently Asked Questions about NotebookLM
What is NotebookLM?
NotebookLM is a Model Context Protocol (MCP) server that enables ai agents to interact with google notebooklm and gemini api for document analysis, deep research, and notebook creation with enterprise-grade security including post-quantum encryption and 14 security layers. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install NotebookLM?
Install via npm with the command: npx -y @pan-sec/notebooklm-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with NotebookLM?
NotebookLM works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is NotebookLM free to use?
Yes, NotebookLM is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
NotebookLM Alternatives — Similar Browser Automation Servers
Looking for alternatives to NotebookLM? Here are other popular browser automation servers you can use with Claude, Cursor, and VS Code.
Chrome DevTools MCP
★ 40.6kAI-powered Chrome automation server with natural language element detection. Control Chrome browser through MCP protocol for testing, debugging, and performance analysis. Features 91% accuracy in element location, works with free AI models, and suppo
UI TARS Desktop
★ 34.9k📇 🏠 - Browser automation capabilities using Puppeteer, both support local and remote browser connection.
Playwright
★ 32.8kA production-ready browser automation server that enables AI assistants to interact with web pages using tools for navigation, element interaction, and data extraction. It features a built-in Inspector UI and robust crash recovery for reliable automa
Page Agent
★ 18.0kJavaScript in-page GUI agent. Control web interfaces with natural language.
Chrome
★ 11.7kAn extension-based MCP server that enables AI assistants to control your browser, leveraging existing sessions and login states for automation and content analysis. It provides over 20 tools for semantic tab search, interactive element manipulation,
LAMDA
★ 7.8kThe most powerful Android RPA agent framework, next generation mobile automation.
Browse More Browser Automation MCP Servers
Explore all browser automation servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up NotebookLM in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use NotebookLM?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.