NotebookLM MCP Server

NotebookLM MCP Server

A remote Model Context Protocol (MCP) server that gives AI agents (Claude, Cursor, Copilot, etc.) full programmatic access to Google NotebookLM via browser automation.

Hosted on Vercel · Browser powered by Browserless.io

🗺️ Architecture

AI Agent (Claude / Cursor)
        │  MCP (Streamable HTTP)
        ▼
  ┌─────────────────────┐
  │  Vercel Function    │  ← Next.js App Router
  │  (TypeScript / MCP) │     mcp-handler adapter
  └─────────┬───────────┘
            │  WebSocket (CDP)
            ▼
  ┌─────────────────────┐
  │  Browserless.io     │  ← Remote headless Chromium
  │  (free tier)        │     stealth mode enabled
  └─────────┬───────────┘
            │  Playwright
            ▼
  ┌─────────────────────┐
  │  Google NotebookLM  │  ← Authenticated via stored cookies
  └─────────────────────┘

⚡ Quick Start

Prerequisites

• Node.js 18+
• A free Browserless.io account → get your API token
• A Google account with access to NotebookLM
• A Vercel account

Step 1 — Clone & install

git clone <your-repo-url>
cd notebooklm-mcp
npm install

Step 2 — Extract Google cookies (one-time)

This step opens a browser window for you to sign in. Runs locally only.

# Install playwright for local cookie extraction
npm install playwright --save-dev
npx playwright install chromium

# Run the extractor
npm run get-cookies

1. A Chrome browser will open → sign in to your Google account
2. Navigate to NotebookLM and verify you can see your notebooks
3. Switch back to the terminal and press Enter
4. The script prints a NOTEBOOKLM_STORAGE_STATE=... value — copy it

Step 3 — Configure environment variables

Copy .env.example to .env.local and fill in your values:

cp .env.example .env.local

# From https://browserless.io → your dashboard
BROWSERLESS_TOKEN=your_token_here

# From the get-cookies script output
NOTEBOOKLM_STORAGE_STATE=eyJjb29...

# Optional: closest region (sfo | lon | sea | fra)
BROWSERLESS_REGION=sfo

Step 4 — Test locally

npm run dev
# MCP endpoint: http://localhost:3000/api/mcp

Step 5 — Deploy to Vercel

# Install Vercel CLI
npm i -g vercel

# Deploy (follow the prompts)
vercel

# Add your environment variables (or use the Vercel dashboard)
vercel env add BROWSERLESS_TOKEN
vercel env add NOTEBOOKLM_STORAGE_STATE
vercel env add BROWSERLESS_REGION

# Deploy to production
vercel --prod

Your MCP server will be live at:

https://your-project.vercel.app/api/mcp

Step 6 — Connect your AI agent

Claude Desktop (~/Library/Application\ Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "notebooklm": {
      "url": "https://your-project.vercel.app/api/mcp"
    }
  }
}

Cursor (.cursor/mcp.json):

{
  "mcpServers": {
    "notebooklm": {
      "url": "https://your-project.vercel.app/api/mcp"
    }
  }
}

🛠️ Available MCP Tools

Notebooks

Sources

Chat / Query

Content Generation

Utility

🔑 Session Management

Google sessions typically last 30–90 days. When your session expires:

1. Run npm run get-cookies again on your local machine
2. Copy the new NOTEBOOKLM_STORAGE_STATE value
3. Update it in Vercel: vercel env rm NOTEBOOKLM_STORAGE_STATE && vercel env add NOTEBOOKLM_STORAGE_STATE
4. Re-deploy: vercel --prod

The `notebooklm_