NotebookLM
Enables direct integration with Google NotebookLM from MCP clients, allowing agents to query notebooks, manage libraries, and get grounded research answers without manual copy-pasting. Uses browser automation to maintain persistent authentication and
What is NotebookLM?
NotebookLM is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables direct integration with google notebooklm from mcp clients, allowing agents to query notebooks, manage libraries, and get grounded research answers without manual copy-pasting. uses browser au...
Enables direct integration with Google NotebookLM from MCP clients, allowing agents to query notebooks, manage libraries, and get grounded research answers without manual copy-pasting. Uses browser automation to maintain persistent authentication and
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables direct integration with Google NotebookLM from MCP c
Use Cases
Maintainer
Works with
Installation
NPM
npx -y notebooklm-mcpManual Installation
npx -y notebooklm-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use NotebookLM
NotebookLM MCP Server bridges AI assistants and Google NotebookLM through browser automation, exposing over a dozen tools for querying notebooks, managing your notebook library, adding sources, and generating audio overviews — all without manual copy-pasting between interfaces. It maintains a persistent authenticated browser session so agents can ask NotebookLM questions and receive grounded answers with citations directly inside their MCP client. Researchers, students, and knowledge workers use it to integrate their NotebookLM libraries into agentic workflows.
Prerequisites
- Node.js 18 or later installed
- Google account with access to NotebookLM (notebooklm.google.com)
- Chrome (stable) installed, or the bundled Patchright Chromium will be used as a fallback
- On headless Linux servers: xvfb-run available for the initial setup_auth step
- An MCP client such as Claude Desktop or Claude Code
Install the package
Install notebooklm-mcp globally or run it directly with npx.
npx notebooklm-mcp@latest
# or add to Claude Code:
claude mcp add notebooklm -- npx notebooklm-mcp@latestAdd the server to your MCP client config
Edit your claude_desktop_config.json or equivalent to register the server.
{
"mcpServers": {
"notebooklm": {
"command": "npx",
"args": ["-y", "notebooklm-mcp@latest"],
"env": {
"HEADLESS": "true",
"NOTEBOOKLM_TRANSPORT": "stdio",
"NOTEBOOKLM_PROFILE": "full"
}
}
}
}Authenticate with Google
Call the setup_auth tool from your MCP client to open a browser window and log in to your Google account. This only needs to be done once; the session is persisted.
Select a notebook
Use the list_notebooks tool to see your NotebookLM library, then select_notebook to set the active notebook for subsequent queries.
Query your notebook
Use the ask_question tool to pose questions to your selected notebook. Responses include grounded answers and citations from your sources.
NotebookLM Examples
Client configuration
Claude Desktop configuration for NotebookLM MCP with common environment variables.
{
"mcpServers": {
"notebooklm": {
"command": "npx",
"args": ["-y", "notebooklm-mcp@latest"],
"env": {
"HEADLESS": "true",
"ANSWER_TIMEOUT_MS": "600000",
"MAX_SESSIONS": "10",
"NOTEBOOKLM_TRANSPORT": "stdio",
"NOTEBOOKLM_PROFILE": "full",
"NOTEBOOKLM_AI_MARKER": "true"
}
}
}
}Prompts to try
Example prompts that exercise NotebookLM MCP tools.
- "List all my NotebookLM notebooks"
- "Select my 'Research 2025' notebook and summarize its key themes"
- "Ask my notebook: What are the main arguments in the uploaded papers about climate policy?"
- "Add this URL as a source to my active notebook: https://example.com/paper.pdf"
- "Generate an audio overview of my current notebook"
- "Search my library for notebooks related to machine learning"Troubleshooting NotebookLM
setup_auth fails or browser window does not appear on a headless Linux server
Wrap the server launch with xvfb-run to provide a virtual display: xvfb-run npx notebooklm-mcp@latest. The initial auth requires a visible browser window; subsequent runs can be headless.
ask_question times out before receiving an answer
Increase the ANSWER_TIMEOUT_MS environment variable. NotebookLM can take several minutes for complex questions; the default is 600000ms (10 minutes). Set it higher if needed.
Authentication session expires and queries start failing
Call the re_auth tool from your MCP client to refresh the session without restarting the server. If re_auth fails, call setup_auth again to perform a full re-login.
Frequently Asked Questions about NotebookLM
What is NotebookLM?
NotebookLM is a Model Context Protocol (MCP) server that enables direct integration with google notebooklm from mcp clients, allowing agents to query notebooks, manage libraries, and get grounded research answers without manual copy-pasting. uses browser automation to maintain persistent authentication and 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 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 Knowledge & Memory Servers
Looking for alternatives to NotebookLM? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory 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.