NotebookLM Connector
About
[Claude Code Plugin] Query Google NotebookLM directly from Claude Code via Chrome browser automation — get source-grounded, citation-backed answers with automatic follow-up analysis, all without leaving your terminal.
Details
- Author
- leejuoh
- Categories
- Productivity, Other, Automation
Jump to
Setup
Install NotebookLM Connector in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/leejuoh/claude-code-zero
Follow the installation instructions in the repository README, then restart your MCP client.
Import web pages and YouTube videos to NotebookLM with one click. Trusted by 200,000+ users.
Query your Google NotebookLM notebooks directly from Claude Code — source-grounded answers without leaving the terminal.
Working with external documentation in Claude Code means bad trade-offs: feeding entire docs into context burns tokens, Claude may hallucinate when it doesn't have the information, and copy-pasting between NotebookLM and your editor kills flow.
This plugin bridges Claude Code and NotebookLM through Chrome automation. You ask a question in natural language, and it routes to NotebookLM — which answers strictly from your uploaded documents. Coverage analysis detects gaps and sends follow-up queries (default 3 rounds, configurable viamax_followups) before presenting the final answer with citations.
Per-user settings are read from the skill config:
- Google Chrome or Microsoft Edge
- Claude in Chrome extensionv1.0.36+
- Claude Code CLIv2.0.73+
- Paid Claude plan(Pro, Max, Teams, or Enterprise)
- Google accountlogged intoNotebookLM
/plugin install notebooklm-connector@claude-code-zero
Start Claude Code with Chrome integration:claude --chrome
"Add https://notebooklm.google.com/notebook/abc123 to my notebooks" "What authentication methods does the API support?" "Show my notebooks" "Search notebooks about frontend" "Disable the gemini-docs notebook" "Remove notebook abc123" "Show notebook abc123"
Programmatic access to Google NotebookLM — via command-line interface (CLI) or Model Context Protocol (MCP) server.
Let your CLI agents (Claude, Cursor, Codex...) chat directly with NotebookLM for zero-hallucination answers based on your own notebooks
Great Question is an Agentic UX research platform for product builders. Its MCP lets AI agents create studies directly from any AI tool, surface insights, find the right research candidates, and query your entire research repository.
Create AI-moderated interviews and surveys via MCP and share survey links with participants instantly.
Multi-round AI debates between GPT, DeepSeek, Groq, and Claude — all models argue, critique, and synthesize inside your coding assistant.
Personal Knowledge Base MCP — 22 tools for AI agents to access your curated reading intelligence.
Give your AI assistant the ability to identify cognitive blind spots. The official Model Context Protocol (MCP) server for cognitivebiaslabs.com.
A cognitive framework selector to help choose the right mental models and thinking frameworks for any situation.
Control your computer's mouse, keyboard, and perform OCR using PyAutoGUI and RapidOCR. Works on Windows, with potential support for other platforms.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
