jacob-bd/gemini-notebook-mcp-cli

Programmatic access to Gemini Notebook - via command-line interface (CLI), Model Context Protocol (MCP) server, and AI agent skills.

gemini‑notebook‑mcp‑cli

What it is – A Python package that ships a command‑line tool (nlm) and a Model‑Context‑Protocol (MCP) server (notebooklm‑mcp). It lets you programmatically control Google Gemini Notebook (formerly Google NotebookLM) and expose the same functionality to AI agents such as Claude, Cursor, or Gemini‑CLI.

Why it matters – Gemini Notebook is Google’s personal‑knowledge‑base service that can store notebooks, sources, audio/video “studio” artifacts, and interactive reports. By providing a stable CLI and an MCP endpoint, this project makes the notebook usable from scripts, CI pipelines, or other AI assistants that speak the MCP protocol.

Quick start (3 commands)

  1. Install – uv tool install notebooklm-mcp-cli (or pip install notebooklm-mcp-cli).
  2. Log in – nlm login (opens a browser, extracts Google cookies, and stores them, optionally encrypted in the OS keychain).
  3. Connect tools – nlm setup runs an interactive wizard that discovers local AI tools (Claude, Cursor, Gemini‑CLI, Copilot, etc.) and registers the MCP server with them.

Core capabilities

Feature CLI command MCP action (exposed to agents)
List notebooks nlm notebook list notebook_list
Create notebook nlm notebook create "My Project" notebook_create
Add sources (URL, text, Drive file) nlm source add <nb> --url … source_add
Query notebook (adds to web UI) nlm notebook query "…" notebook_query
Manage chat sessions nlm chats list/get/export chat_list, chat_get, chat_export
Generate studio content (audio, video, slides) nlm studio create … studio_create
Download artifacts nlm download <type> … download_artifact
Batch / pipeline workflows nlm batch …, nlm pipeline run batch, pipeline
Tagging & smart selection nlm tag add/list/select tag
Usage / quota info nlm usage usage_get
Credential protection nlm auth storage set protected –

How agents use it

  1. Run the MCP server – notebooklm-mcp starts a local HTTP endpoint.
  2. Agent registration – The wizard (nlm setup add <tool>) writes a JSON configuration into the target AI tool (Claude Desktop, Cursor, etc.).
  3. Natural‑language calls – Once registered, you can ask the agent: “Create a notebook about quantum computing and generate a podcast.” The agent translates the request into MCP calls (notebook_create, studio_create, …) and the server talks to Gemini Notebook on your behalf.

Installation options

Method Command
uv (recommended) uv tool install notebooklm-mcp-cli
uvx (run without installing) uvx --from notebooklm-mcp-cli nlm --help
pip pip install notebooklm-mcp-cli
pipx pipx install notebooklm-mcp-cli
From source Clone the repo and uv tool install .

Both nlm (CLI) and notebooklm-mcp (MCP server) become available on your $PATH.

Authentication & security

  • Uses Google cookies extracted from a browser session (auto‑mode or manual file import).
  • Optional protected storage encrypts the saved cookies with the OS keychain; plain‑file storage is still supported for headless or Docker setups.
  • Supports multiple profiles (--profile work, --profile personal).
  • Provides a head‑less refresh command (nlm auth refresh) for cron‑based token renewal.
  • Disclaimer – The tool talks to undocumented internal Google APIs; usage is intended for personal/experimental purposes and may violate Google’s Terms of Service.

Maintenance & upgrades

  • Upgrade via the same installer you used (uv tool upgrade notebooklm-mcp-cli, pip install --upgrade …, etc.).
  • Legacy packages (notebooklm-cli, notebooklm-mcp-server) are deprecated; the README includes a migration guide.
  • All configuration and cached data live under ~/.notebooklm-mcp-cli; backups are made automatically before any change.

License & community

  • License: MIT (see LICENSE).
  • Published on PyPI (badge shows current version and download stats).
  • The author encourages donations via Buy‑Me‑A‑Coffee to fund ongoing testing.

Bottom line

gemini-notebook-mcp-cli is a practical bridge that turns Google’s Gemini Notebook into a programmable service and makes it reachable by a growing ecosystem of AI assistants. If you already use Claude, Cursor, Gemini‑CLI, or similar agents and want them to read/write notebooks, generate audio/video, or share artifacts automatically, this package gives you a ready‑made CLI + MCP server with minimal configuration.

Related

  • Project
    teng-lin/notebooklm-py

    An unofficial Python client/CLI for Google’s Gemini Notebook (formerly Notebook LM). It lets you program‑matically create notebooks, add many source types, ask Gemini‑powered questions, generate audio/video/slides/quiz/flashcards/mind‑maps, and batch‑download the results. Designed for research automation, LLM‑agent integration (Claude Code, Codex, etc.), and head‑less scripting via a Python API, MCP server, or REST server. Uses undocumented Google APIs, so it may break and is rate‑limited.

  • Project
    google-gemini/gemini-cli

    An open-source AI agent for the terminal that provides direct access to Gemini models for code analysis, automation, and system integration.

  • Project
    claude-world/notebooklm-skill

    An automation tool and MCP server for Google NotebookLM that enables creating notebooks, performing grounded research, and generating artifacts via CLI or AI agents.

  • Project
    tmc/nlm

    A single-binary CLI client and MCP server for NotebookLM that enables terminal-based interaction, automation, and AI agent integration via a reverse-engineered wire protocol.

  • Project
    yeahhe365/Gemini-Nexus

    Gemini Nexus is a Chrome MV3 extension that adds a native AI assistant to the browser. It supports Google Gemini (both the web UI via reverse‑engineered tokens and the official API) and many OpenAI‑compatible services. The extension provides a side‑panel, a floating selection toolbar, image/screenshot input, and a Chrome‑DevTools‑based control loop so the LLM can navigate pages, click elements, fill forms, run scripts, and call external tool‑servers (MCP). It includes context‑management features, watermark removal for Gemini images, and a full build/publish workflow. The Gemini‑Web integration may violate Google’s Terms of Service, so users must accept the associated risk.