NotebookLM Secure
Secure NotebookLM MCP Server - Query Google NotebookLM from Claude/AI agents with 17 security hardening layers
What is NotebookLM Secure?
NotebookLM Secure is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to secure notebooklm mcp server - query google notebooklm from claude/ai agents with 17 security hardening layers
Secure NotebookLM MCP Server - Query Google NotebookLM from Claude/AI agents with 17 security hardening layers
This server falls under the Browser Automation category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Secure NotebookLM MCP Server - Query Google NotebookLM from
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx notebooklm-mcp-secureConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use NotebookLM Secure
NotebookLM Secure is a hardened MCP server that lets Claude and other AI agents query Google NotebookLM notebooks directly, with 17 security layers including post-quantum encryption (ML-KEM-768 + ChaCha20-Poly1305), hash-chained audit logs, secrets scanning, and MCP token authentication. It exposes 48 tools covering notebook creation, source management, audio/video overview generation, structured data extraction, deep research via Gemini, and webhook integration. Developers and security-conscious teams use it to give AI assistants grounded, source-cited answers from their private NotebookLM knowledge bases without sacrificing enterprise compliance requirements.
Prerequisites
- Node.js 18+ and npx available on your system
- A Google account with access to NotebookLM (accounts.google.com)
- Chrome browser installed (used for the initial Google authentication flow)
- Optional: a Google Gemini API key (GEMINI_API_KEY) for deep research and document upload features
- An MCP-compatible client such as Claude Desktop, Claude Code, Cursor, or VS Code with Copilot
Install the package via npx
The server ships as a scoped npm package. You can run it directly with npx without a global install. Test that it starts correctly before adding it to your MCP client.
npx @pan-sec/notebooklm-mcp@latestAdd the server to Claude Code
Use the Claude Code CLI to register the MCP server. This minimal command enables core NotebookLM querying without Gemini features.
claude mcp add notebooklm -- npx @pan-sec/notebooklm-mcp@latestEnable authentication and optional Gemini features
For production use, enable token-based auth and optionally add a Gemini API key to unlock deep research, document upload, and query-with-web-search capabilities.
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@latestAuthenticate with Google
On first run, call the setup_auth tool (or ask your AI assistant to authenticate). A Chrome window will launch automatically to complete the Google OAuth flow. The session is encrypted and persisted locally.
Configure Claude Desktop (alternative client)
If using Claude Desktop instead of Claude Code, add the server block to your claude_desktop_config.json file.
{
"mcpServers": {
"notebooklm": {
"command": "npx",
"args": ["@pan-sec/notebooklm-mcp@latest"],
"env": {
"NLMCP_AUTH_ENABLED": "true",
"NLMCP_AUTH_TOKEN": "your-secret-token",
"GEMINI_API_KEY": "your-gemini-api-key"
}
}
}
}Adjust the tool profile (optional)
The NOTEBOOKLM_PROFILE variable controls which of the 48 tools are visible. Use 'minimal' for basic Q&A, 'standard' for most workflows, or 'full' to expose all enterprise and compliance tools.
export NOTEBOOKLM_PROFILE=standardNotebookLM Secure Examples
Client configuration
Claude Desktop config with authentication and Gemini deep research enabled.
{
"mcpServers": {
"notebooklm": {
"command": "npx",
"args": ["@pan-sec/notebooklm-mcp@latest"],
"env": {
"NLMCP_AUTH_ENABLED": "true",
"NLMCP_AUTH_TOKEN": "your-secret-token",
"GEMINI_API_KEY": "your-gemini-api-key",
"NOTEBOOKLM_PROFILE": "standard",
"GEMINI_DEEP_RESEARCH_ENABLED": "true"
}
}
}
}Prompts to try
Example queries once the server is connected and authenticated.
- "Create a new notebook from this URL and this PDF, then give me a summary"
- "Ask my research notebook: what are the main findings on transformer attention?"
- "Generate a podcast-style audio overview of my security notebook"
- "Extract a structured data table from my market research notebook"
- "Run deep research on quantum-resistant cryptography and save it to a new notebook"
- "What did I ask my fine-tuning notebook last week? Show my query history"Troubleshooting NotebookLM Secure
Chrome does not open for authentication or the auth flow hangs
Make sure Chrome is installed and accessible on your PATH. On Linux you may need to set DISPLAY or run in a desktop environment. Call the re_auth tool to restart the authentication flow without restarting the server.
Gemini tools (deep_research, gemini_query, upload_document) are not available
These tools require a valid GEMINI_API_KEY environment variable and GEMINI_DEEP_RESEARCH_ENABLED=true. Verify the key is set correctly and that your profile is not 'minimal', which hides Gemini tools.
Server returns 'auth token mismatch' or brute-force lockout errors
Regenerate a fresh NLMCP_AUTH_TOKEN with 'openssl rand -base64 32', update it in your MCP client config, and restart the server. The lockout resets after 15 minutes by default.
Frequently Asked Questions about NotebookLM Secure
What is NotebookLM Secure?
NotebookLM Secure is a Model Context Protocol (MCP) server that secure notebooklm mcp server - query google notebooklm from claude/ai agents with 17 security hardening layers It connects AI assistants to external tools and data sources through a standardized interface.
How do I install NotebookLM Secure?
Follow the installation instructions on the NotebookLM Secure GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with NotebookLM Secure?
NotebookLM Secure works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is NotebookLM Secure free to use?
Yes, NotebookLM Secure is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
NotebookLM Secure Alternatives — Similar Browser Automation Servers
Looking for alternatives to NotebookLM Secure? 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 Secure 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 Secure?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.