mcp-server

notebooklm-mcp: AI-driven Q&A

Name: notebooklm-mcp: AI-driven Q&A
Author: roomi-fields

Get citation-backed Q&A and content generation with notebooklm-mcp, for founders using Claude Code, Codex, and more.

From the repo · “Google NotebookLM over MCP + a local HTTP REST API. Citation-backed Q&A, audio/video/content generation, multi-account rotation. For Claude Code, Codex, Cursor, n8n, Zapier, Make.”

205 stars+9★ this week64 forksTypeScriptGuide quality 8/10 · reviewed Jul 30Updated 10/23/2026100% free · open source

What it does

NotebookLM-MCP provides a local HTTP REST API for Google NotebookLM, enabling citation-backed Q&A, audio/video/content generation, and multi-account rotation for various integrations like Claude Code, Codex, Cursor, n8n, Zapier, and Make.

When to use it

•You need to generate content with citations for your startup's blog or social media
•You want to automate tasks using tools like n8n, Zapier, or Make with the power of NotebookLM
•You require a local API for audio/video generation or other media creation tasks

Ready-to-paste prompt

curl -X POST -H 'Content-Type: application/json' -d '{"prompt":"Explain the concept of artificial intelligence"}' http://localhost:3000/generate

Heads up: Ensure you have a Google NotebookLM API key and properly configured environment variables or a config file to authenticate your API requests

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/notebooklm-mcp && curl -fsSL https://workflowstacks.com/api/skills/notebooklm-mcp/claude-skill -o ~/.claude/skills/notebooklm-mcp/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How notebooklm-mcp: AI-driven Q&A works

Codeflow

Free to inspect

Notebooklm-mcp: AI-driven Q&A is a large TypeScript project (~36k lines across 189 code files, plus 84 test files). You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, MIT license, has a test suite.

Size

Large codebase

~36k lines · 189 code files · ~5 h to skim

Setup

Install as a skill / plugin

Add it to Claude Code (or your AI tool) with one command — 1 skill inside. Nothing to run yourself.

Runs on

Inside your AI tool

Helper scripts use Node.js · Docker · needs API keys

TypeScript 75%PowerShell 19%JavaScript 3%MDX 2%Shell 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
src/index.ts
Where the program starts running
3
.env.example
The API keys and settings you must provide

What's in each folder

src/Core code — the actual logic98 files

skills/Prompts, skills & agent definitions4 files

docs/Documentation6 files

scripts/Helper scripts120 files

website/Project website35 files

deployment/Deployment / infrastructure34 files

deploy-package/Folder2 files

mcpb/Folder2 files

READMEHas testsDocumentedCI checksDocker readyMIT licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/notebooklm-mcp && curl -fsSL https://workflowstacks.com/api/skills/notebooklm-mcp/claude-skill -o ~/.claude/skills/notebooklm-mcp/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

roomi-fields

Language

TypeScript