NoteBook MCP
Enables AI agents to query personal Google NotebookLM notebooks using a persistent browser session for instant queries without an official API.
README
NoteBook MCP
An MCP (Model Context Protocol) server that enables AI agents (like Claude Desktop) to query your personal Google NotebookLM notebooks.
It uses a persistent, local browser session (via Playwright) to bypass the lack of an official API, allowing for "warm start" instant queries.
✨ Features
- Zero-API Access: Works with any Google account; no enterprise API required.
- Warm Start: Keeps a browser instance open in the background, making creating queries instant (after the first load).
- Persistent Auth: Uses standard browser cookies to maintain your session.
- MCP Compliant: Works out-of-the-box with any MCP client.
🚀 Setup
1. Installation
Clone this repository and install dependencies:
git clone https://github.com/your-username/notebook-mcp.git
cd notebook-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
playwright install chromium
2. Authentication (Manual Cookie Export)
Since Google's security prevents automated headless logins, you must export your cookies:
- Log in to NotebookLM in your regular Chrome browser.
- Open DevTools (Right-click -> Inspect) -> Application -> Cookies.
- Select
https://notebooklm.google.com. - Select all cookies (Cmd/Ctrl+A) and Copy (Cmd/Ctrl+C).
- Paste them into
notebooklm_cookies.jsonin this directory.
Note: Your
notebooklm_cookies.jsonis git-ignored by default. Never commit it!
💻 Usage
As an MCP Server (Claude Desktop)
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"notebooklm": {
"command": "/absolute/path/to/notebook-mcp/.venv/bin/python3",
"args": ["/absolute/path/to/notebook-mcp/server.py"]
}
}
}
As a Library
You can use the session manager in your own Python scripts:
from notebook_session import NotebookLMSession
session = NotebookLMSession(headless=True)
answer = session.query("https://notebooklm.google.com/notebook/...", "Summarize this doc")
print(answer)
⚠️ Limitations
- Session Expiry: Google cookies expire every few weeks. If the tool stops working, re-export your cookies.
- Single Threaded: The browser automation is not designed for high-concurrency requests.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.