FastMCP FastMCP
Sign In
N

NotebookLM

1-Click Ready

Empower your CLI agents with zero-hallucination answers from your own docs. NotebookLM MCP Server co...

297 views
8 installs
Updated Nov 21, 2025
Audited
Content Management
Empower your CLI agents with zero-hallucination answers from your own docs. NotebookLM MCP Server connects AI tools like Claude, Cursor, and Codex directly to Google’s NotebookLM, ensuring every answer is accurate, current, and citation-backed. Skip error-prone manual copy-paste—let your AI assistant research, synthesize, and reference across your documents for confident coding. All queries are grounded in your uploads, eliminating invented APIs or outdated info. Manage notebooks, automate deep research, and achieve seamless collaboration between multiple tools using a shared, always-relevant knowledge base. Spend less time debugging and more time building with trustworthy, source-based answers.

1. Authenticate (one-time)

Say in your chat (Claude/Codex):

"Log me in to NotebookLM"

A Chrome window opens → log in with Google

2. Create your knowledge base

Go to notebooklm.google.com → Create notebook → Upload your docs:

  • 📄 PDFs, Google Docs, markdown files
  • 🔗 Websites, GitHub repos
  • 🎥 YouTube videos
  • 📚 Multiple sources per notebook

Share: ⚙️ Share → Anyone with link → Copy

3. Let Claude use it

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

That's it. Claude now asks NotebookLM whatever it needs, building expertise before writing code.

Real-World Example

Building an n8n Workflow Without Hallucinations

Challenge: n8n's API is new — Claude hallucinates node names and functions.

Solution:

  1. Downloaded complete n8n documentation → merged into manageable chunks
  2. Uploaded to NotebookLM
  3. Told Claude: "Build me a Gmail spam filter workflow. Use this NotebookLM: [link]"

Watch the AI-to-AI conversation:

Claude → "How does Gmail integration work in n8n?"
NotebookLM → "Use Gmail Trigger with polling, or Gmail node with Get Many..."

Claude → "How to decode base64 email body?"
NotebookLM → "Body is base64url encoded in payload.parts, use Function node..."

Claude → "How to parse OpenAI response as JSON?"
NotebookLM → "Set responseFormat to json, use {{ $json.spam }} in IF node..."

Claude → "What about error handling if the API fails?"
NotebookLM → "Use Error Trigger node with Continue On Fail enabled..."

Claude → ✅ "Here's your complete workflow JSON..."

Result: Perfect workflow on first try. No debugging hallucinated APIs.

Tools

ask_question

# Conversational Research Partner (NotebookLM • Gemini 2.5 • Session RAG) ## No Active Notebook - Visit https://notebooklm.google to create a notebook and get a share link - Use **add_notebook** to a...

list_notebooks

List all library notebooks with metadata (name, topics, use cases, URL). Use this to present options, then ask which notebook to use for the task.

select_notebook

Set a notebook as the active default (used when ask_question has no notebook_id). ## When To Use - User switches context: "Let's work on React now" - User asks explicitly to activate a notebook - Obv...

remove_notebook

Dangerous — requires explicit user confirmation. ## Confirmation Workflow 1) User requests removal ("Remove the React notebook") 2) Look up full name to confirm 3) Ask: "Remove '[notebook_name]' from...

get_library_stats

Get statistics about your notebook library (total notebooks, usage, etc.)

Quick Start

View on GitHub

More for Content Management

View All →

Report Issue

Thank you! Your issue report has been submitted successfully.