NotebookLM MCP server

Automates Google NotebookLM interactions through browser automation, enabling document querying and notebook library management with stealth capabilities to avoid detection.
Back to servers
Setup instructions
Provider
Please Prompto!
Release date
Oct 17, 2025
Language
Go
Stats
201 stars

NotebookLM MCP Server allows your CLI agents (Claude, Cursor, Codex, etc.) to directly interact with Google's NotebookLM for accurate, zero-hallucination responses based on your own knowledge bases. This integration eliminates the manual copy-paste workflow between NotebookLM and your editor, enabling your AI assistants to perform deep, iterative research before writing code.

What It Solves

When AI assistants try to search through local documentation, they face several challenges:

  • High token consumption from reading multiple files
  • Inaccurate retrieval that misses context
  • Hallucinations when information gaps exist
  • Slow and expensive repeated file reading

NotebookLM MCP addresses these problems by connecting your AI tools directly to Google's NotebookLM, which provides synthesized answers from your documentation with zero hallucinations.

Installation

Claude Code

claude mcp add notebooklm npx notebooklm-mcp@latest

Codex

codex mcp add notebooklm -- npx notebooklm-mcp@latest

Other MCP Clients

For Gemini:

gemini mcp add notebooklm npx notebooklm-mcp@latest

For Cursor, add to ~/.cursor/mcp.json:

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

For amp:

amp mcp add notebooklm -- npx notebooklm-mcp@latest

For VS Code:

code --add-mcp '{"name":"notebooklm","command":"npx","args":["notebooklm-mcp@latest"]}'

Generic MCP configuration:

{
  "mcpServers": {
    "notebooklm": {
      "command": "npx",
      "args": ["notebooklm-mcp@latest"]
    }
  }
}

Quick Start

1. Install the MCP server

Follow the installation instructions above for your preferred AI tool.

2. Authenticate (one-time)

In your chat with Claude, Codex, or other AI tool, say:

"Log me in to NotebookLM"

A Chrome window will open where you'll need to log in with your Google account.

3. Create your knowledge base

Go to notebooklm.google.com, create a notebook, and upload your documentation:

  • PDFs, Google Docs, markdown files
  • Websites, GitHub repositories
  • YouTube videos
  • Multiple sources per notebook

Share your notebook by clicking ⚙️ Share → Anyone with link → Copy

4. Let your AI assistant use it

"I'm building with [library]. Here's my NotebookLM: [link]"

Your AI assistant can now ask NotebookLM whatever it needs, building expertise before writing code.

Tool Profiles

You can reduce token usage by loading only the tools you need:

Available Profiles

Profile Tools Use Case
minimal 5 Query-only: ask_question, get_health, list_notebooks, select_notebook, get_notebook
standard 10 + Library management: setup_auth, list_sessions, add_notebook, update_notebook, search_notebooks
full 16 All tools including cleanup_data, re_auth, remove_notebook, reset_session, close_session, get_library_stats

Configure via CLI

# Check current settings
npx notebooklm-mcp config get

# Set a profile
npx notebooklm-mcp config set profile minimal
npx notebooklm-mcp config set profile standard
npx notebooklm-mcp config set profile full

# Disable specific tools (comma-separated)
npx notebooklm-mcp config set disabled-tools "cleanup_data,re_auth"

# Reset to defaults
npx notebooklm-mcp config reset

Configure via Environment Variables

# Set profile
export NOTEBOOKLM_PROFILE=minimal

# Disable specific tools
export NOTEBOOKLM_DISABLED_TOOLS="cleanup_data,re_auth,remove_notebook"

Settings are saved to ~/.config/notebooklm-mcp/settings.json and persist across sessions.

Common Commands

Intent Say Result
Authenticate "Open NotebookLM auth setup" or "Log me in to NotebookLM" Chrome opens for login
Add notebook "Add [link] to library" Saves notebook with metadata
List notebooks "Show our notebooks" Lists all saved notebooks
Research first "Research this in NotebookLM before coding" Multi-question session
Select notebook "Use the React notebook" Sets active notebook
Update notebook "Update notebook tags" Modify metadata
Remove notebook "Remove [notebook] from library" Deletes from library
View browser "Show me the browser" Watch live NotebookLM chat
Fix auth "Repair NotebookLM authentication" Clears and re-authenticates
Switch account "Re-authenticate with different Google account" Changes account
Clean restart "Run NotebookLM cleanup" Removes all data for fresh start
Keep library "Cleanup but keep my library" Preserves notebooks
Delete all data "Delete all NotebookLM data" Complete removal

FAQ

Is it really zero hallucinations?
Yes. NotebookLM is specifically designed to only answer from uploaded sources. If it doesn't know, it says so.

What about rate limits?
Free tier has daily query limits per Google account. Quick account switching supported for continued research.

How secure is this?
Chrome runs locally. Your credentials never leave your machine. Use a dedicated Google account if concerned.

Can I see what's happening?
Yes! Say "Show me the browser" to watch the live NotebookLM conversation.

What makes this better than Claude's built-in knowledge?
Your docs are always current. No training cutoff. No hallucinations. Perfect for new libraries, internal APIs, or fast-moving projects.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "notebooklm" '{"command":"npx","args":["notebooklm-mcp@latest"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "notebooklm": {
            "command": "npx",
            "args": [
                "notebooklm-mcp@latest"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

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

2. Add this to your configuration file:

{
    "mcpServers": {
        "notebooklm": {
            "command": "npx",
            "args": [
                "notebooklm-mcp@latest"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later