NotebookLM

v1.5.9Knowledge & Memorystable

📇 🏠 🍎 🪟 🐧 - Full automation of Google NotebookLM — Q&A with citations, audio podcast

aianthropicautomationcitationsclaude
Share:
80
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 📇 🏠 🍎 🪟 🐧 - full automation of google notebooklm — q&a with citations, audio podcast

📇 🏠 🍎 🪟 🐧 - Full automation of Google NotebookLM — Q&A with citations, audio podcast

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP protocol support

Use Cases

Google NotebookLM automation
Q&A with citations
Audio podcast generation
roomi-fields

Maintainer

LicenseMIT License
Languagetypescript
Versionv1.5.9
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y @roomi-fields/notebooklm-mcp

Manual Installation

npx -y @roomi-fields/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

The notebooklm-mcp package provides both a full MCP server for AI clients (Claude Code, Cursor, Codex) and a 33-endpoint HTTP REST API for automation platforms (n8n, Zapier, Make.com), giving programmatic access to Google NotebookLM's Q&A with citation extraction, full Studio content generation (audio podcasts, videos, infographics, reports, presentations, and data tables), multi-notebook management, source uploads, and multi-account rotation with automatic re-authentication. The tool namespace uses dot notation (notebook.ask, source.add, session.list) with backward-compatible flat aliases, and has been batch-tested against overnight runs of 1,000+ questions with a 97% citation extraction success rate.

Prerequisites

  • Node.js 18 or higher
  • A Google account for authentication (a dedicated automation account is recommended)
  • Chrome browser available on the system (the server uses browser automation)
  • An MCP-compatible client or HTTP automation platform
1

Install via npx (quickest for MCP mode)

Run the package directly with npx. The package name on npm is @roomi-fields/notebooklm-mcp.

npx -y @roomi-fields/notebooklm-mcp
2

Or clone and build for HTTP REST API mode

Clone the repository, install dependencies, build, and run the one-time Google authentication setup if you plan to use the HTTP API for n8n/Zapier/Make integrations.

git clone https://github.com/roomi-fields/notebooklm-mcp.git
cd notebooklm-mcp
npm install && npm run build
npm run setup-auth   # opens Chrome for Google login
npm run start:http   # starts REST API on port 3000
3

Authenticate with Google

The first time you use the server in MCP mode, tell your AI client 'Log me in to NotebookLM'. A Chrome window will open — log in with your Google account. Sessions are saved and auto-renewed.

4

Add to your MCP client configuration

Register the server in your MCP client config using the npx command. The server will start Chrome automatically when the MCP client initializes it.

5

Start using NotebookLM tools

The MCP server exposes tools across 9 namespaces: notebook (ask, create, delete), source (add, list), session (list, reauth), studio (generate audio/video/infographic/report), vault (batch), and server (health). Legacy flat tool names also work.

NotebookLM Examples

Client configuration

MCP configuration using the published npm package. No environment variables required — authentication is handled interactively via the setup-auth flow.

{
  "mcpServers": {
    "notebooklm": {
      "command": "npx",
      "args": ["-y", "@roomi-fields/notebooklm-mcp"]
    }
  }
}

Prompts to try

Example prompts leveraging NotebookLM's Q&A, content generation, and source management tools.

- "Ask my NotebookLM notebook 'What are the key findings in chapter 3?' and show the citations."
- "Add this PDF URL as a source to my research notebook: https://example.com/paper.pdf"
- "Generate an audio podcast overview of my 'AI Research' notebook in English."
- "List all my notebooks and show their source counts."
- "Run a batch of 10 questions against my notebook and save the citation-backed answers."

Troubleshooting NotebookLM

Chrome does not open for authentication or the setup-auth command hangs

Ensure Chrome is installed at a standard system path. On Linux, you may need to install google-chrome or chromium-browser. For Docker/headless deployments, use the Docker guide with noVNC (port 6080) to authenticate visually: http://localhost:6080/vnc.html

Authentication expires mid-session and tools start returning errors

The server includes automatic re-authentication using stored credentials. If re-auth fails, run 'npm run setup-auth' again to refresh the Google session. For overnight batch runs, the multi-account rotation feature (v1.4.0+) handles session expiry automatically.

The add_source tool reports success but the source count does not increase

This was a known issue with the 2026 NotebookLM UI (fixed in v1.5.8+). Update to the latest version with 'npx -y @roomi-fields/notebooklm-mcp@latest'. The fix uses count-based detection that runs on every poll cycle instead of only after the upload dialog closes.

Frequently Asked Questions about NotebookLM

What is NotebookLM?

NotebookLM is a Model Context Protocol (MCP) server that 📇 🏠 🍎 🪟 🐧 - full automation of google notebooklm — q&a with citations, audio podcast 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 @roomi-fields/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": { "command": "npx", "args": ["-y", "@roomi-fields/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