NotebookLM MCP Server

Let your AI agents chat directly with Google NotebookLM for zero-hallucination answers.

English • Español • Français • Português • Deutsch

Installation • Authentication • Quick Start • Claude Code • Documentation • Development

The Solution

The NotebookLM MCP Server brings the power of Google's NotebookLM directly into your AI-augmented workflow. Built natively in TypeScript using the Model Context Protocol, it allows agents to read, search, and manage your notebooks as if they were local files.

---

🚀 Installation

1. Global Installation (Recommended)

You can install the server directly from NPM:

npm install -g notebooklm-mcp-server

[!NOTE] Auto-update: The server automatically checks for new versions at startup. If an update exists, it will install itself and ask you to restart to ensure you always have the latest Google fixes.

2. Direct usage with NPX (Zero-Config)

If you don't want to install it globally, you can run it directly:

npx notebooklm-mcp-server auth   # To log in
npx notebooklm-mcp-server start  # To run the server

---

🔑 Authentication

Before using the server, you must link it to your Google Account. This version uses a secure, persistent browser session:

1. Run the authentication command:

   npx notebooklm-mcp-server auth
   

2. A browser window will open. Log in with your Google account.
3. Close the browser once you see your notebooks. Your session is now securely saved locally.

[!TIP] Session Expired? If your agent receives authentication errors, simply ask it to run the command npx notebooklm-mcp-server refresh_auth. It will automatically open the browser for you to renew the session without leaving your chat.

---

⚡ Quick Start

🤖 Claude Desktop

Add the following to your claude_desktop_config.json:

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

💻 Visual Studio Code

Since VS Code does not support MCP natively yet, you must use an extension:

Option A: Using Cline (Recommended)

1. Open Cline Settings in VS Code.
2. Scroll to the MCP Servers section.
3. Click Add New MCP Server.
4. Use the following configuration:
   • Name: notebooklm
   • Command: npx -y notebooklm-mcp-server start

Option B: Using MCP Client

1. Install the extension from the Marketplace.
2. Open your VS Code settings.json.
3. Add the server under mcp.servers:

   "mcp.servers": {
     "notebooklm": {
       "command": "npx",
       "args": ["-y", "notebooklm-mcp-server", "start"]
     }
   }
   

🌌 Antigravity

Antigravity supports MCP natively. You can add the server by editing your global configuration file:

1. Locate your mcp.json:

   • Windows: %APPDATA%\antigravity\mcp.json
   • macOS: ~/Library/Application Support/antigravity/mcp.json
   • Linux: ~/.config/antigravity/mcp.json

2. Add the server to the mcpServers object:

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

3. Restart Antigravity: The new tools will appear in your sidebar instantly.

---

💎 Gemini CLI

Run the following command in your terminal to add the notebooklm skill:

gemini mcp add notebooklm --scope user -- npx -y notebooklm-mcp-server start

---

🤖 Claude Code Skill

Add it instantly to Claude Code:

claude skill add notebooklm -- "npx -y notebooklm-mcp-server start"

---

📖 Documentation

The following tools are available through this MCP server:

📒 Notebook Management

Tool	Description
notebook_list	Lists all notebooks in your account.
notebook_create	Creates a new notebook with a title.
notebook_rename	Renames an existing notebook.
notebook_delete	Deletes a notebook (Warning: Destructive).

🖇️ Source Management

Tool	Description
notebook_add_url	Adds a website or YouTube video as a source.
notebook_add_text	Adds custom text content as a source.
notebook_add_local_file	Uploads a local PDF, Markdown or Text file.
notebook_add_drive	Adds a file from Google Drive (Docs, Slides, etc).
source_delete	Removes a source from a notebook.
source_sync	Syncs a Drive source to get the latest version.

🔍 Research & Query

Tool	Description
notebook_query	Asks a grounded question to a specific notebook.
research_start	Starts a web/drive research task.
research_poll	Polls for research status and results.
research_import	Imports research results as permanent sources.

🎨 Studio & Generation

Tool	Description
audio_overview_create	Generates an Audio Overview (podcast).
studio_poll	Checks status of generated audio/video artifacts.
mind_map_generate	Generates a Mind Map JSON from sources.

⚙️ System

Tool	Description
refresh_auth	Interactive: Opens a browser to renew your Google session. Use this if tools start failing.

---

🛠️ Development

To contribute or build from source:

git clone https://github.com/moodRobotics/notebook-mcp-server.git
npm install
npm run build

🌐 Localization

This project is available in multiple languages:

• English (Source)
• Español
• Français
• Português
• Deutsch

If you update the English README.md, please ensure the translations are updated accordingly to keep the documentation synchronized.

📄 License

MIT License. Developed with ❤️ by moodRobotics.