claude-world/notebooklm-skill

NotebookLM does the research, Claude writes the content. Research → Synthesis → Content Creation → Publishing. Claude Code Skill + MCP Server.

What it solves

It provides a consistent, automated interface for Google NotebookLM, allowing users and AI agents to interact with the service via a terminal or Model Context Protocol (MCP) server. This removes the need for manual web interaction to create notebooks, ingest sources, and generate grounded content.

How it works

Built on top of notebooklm-py, the project implements an unofficial integration with NotebookLM's web API. It offers a JSON-first CLI for managing notebooks and sources, a set of pre-defined research pipelines for automating content creation (such as turning research into articles or social posts), and a FastMCP server that exposes 13 tools to AI clients like Claude Code or Cursor.

Who it’s for

  • Developers and Power Users who want to automate their research workflows via the command line.
  • AI Agent Users who want to give their LLM agents the ability to create and query grounded notebooks.
  • Researchers who need to batch-process sources and generate various artifacts like audio deep-dives, slides, and reports.

Highlights

  • Mixed-Source Ingestion: Create notebooks using a combination of URLs, raw text, and local files.
  • Grounded Querying: Ask questions with citation metadata to ensure answers are based on the sources.
  • Diverse Artifact Generation: Generate and download a wide variety of outputs including audio (M4A), video (MP4), slides (PDF/PPTX), reports (Markdown), and mind-maps.
  • MCP Integration: A ready-to-use server for seamless integration with MCP-compatible AI clients.
  • Research Pipelines: End-to-end workflows for tasks like research-to-article and batch-digest.

Related

  • Project
    teng-lin/notebooklm-py

    An unofficial Python API and CLI for Google's NotebookLM (Gemini Notebook), enabling programmatic research automation, multimedia content generation, and grounded memory for AI agents.

  • Project
    tmc/nlm

    A single-binary Go client for NotebookLM that provides a scriptable CLI, an interactive chat client, and an MCP server for AI agents.

  • Project
    jacob-bd/gemini-notebook-mcp-cli

    A Python package that provides a command‑line tool (`nlm`) and a Model Context Protocol (MCP) server for programmatic access to Google’s Gemini Notebook. It lets you list/create notebooks, add sources, run AI‑driven queries, generate audio/video/slide content, download artifacts, share notebooks, and integrate the service with AI assistants (Claude, Cursor, Gemini‑CLI, etc.) via automatically generated MCP configurations.

  • Project
    a-bonus/google-docs-mcp

    An MCP server that connects AI assistants to Google Docs, Sheets, Drive, Gmail, and Calendar, enabling LLMs to read and manage Workspace data.

  • Project
    makenotion/notion-mcp-server

    An MCP server that enables AI agents to read, search, and edit Notion workspaces using token-efficient Markdown tools.