NotebookLM

v2.0.0Knowledge & Memorystable

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

mcpnotebooklmgeminiaiclaude
Share:
2,505
Stars
0
Downloads
0
Weekly
0/5

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

Query Google NotebookLM notebooks without manual copy-pasting.
Get grounded research answers from your notebook libraries.
PleasePrompto

Maintainer

LicenseMIT License
Languagetypescript
Versionv2.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y notebooklm-mcp

Manual Installation

npx -y notebooklm-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

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
1

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@latest
2

Add 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"
      }
    }
  }
}
3

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.

4

Select a notebook

Use the list_notebooks tool to see your NotebookLM library, then select_notebook to set the active notebook for subsequent queries.

5

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.

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.

Quick Config Preview

{ "mcpServers": { "notebooklm-mcp-server": { "command": "npx", "args": ["-y", "notebooklm-mcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

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.

33,000+ ServersFree & Open SourceStep-by-Step Guides