It rides internal APIs, and the author says so before you install.

The capability is real and broad — cross-notebook queries and pipelines are things the product's own UI does not offer — but the plumbing is undocumented Google endpoints and browser cookies, which can change without notice. Treat it as a power tool for personal and experimental work, which is the framing the README itself uses.

What it is

One Python package that is both a CLI (nlm) and an MCP server for Gemini Notebook. It uses Google's internal, undocumented APIs and browser cookies rather than a published API, which the README states plainly.

What you get

Notebooks listed and created — notebook_list, notebook_create
Sources added from a URL, plain text, Google Drive or a file, and Drive sources re-synced — source_add, source_sync_drive
A notebook queried with the exchange persisting to the web UI, plus chat sessions listed, read and exported — notebook_query, chat_list, chat_get, chat_export
Studio content generated — audio, video and more — and slide decks revised — studio_create, studio_revise
Artifacts downloaded individually or in bulk across one notebook or all of them — download_artifact, download_all_artifacts
Web and Drive research started from the agent — research_start
Questions asked across several notebooks at once, multi-step pipelines, batch operations, and tag-based selection — cross_notebook_query, pipeline, batch, tag
Notebook sharing, and a nlm doctor command for diagnosing setup problems

Requirements

A Gemini Notebook account and cookies extracted from your browser — the package includes a tool for that. Installed from PyPI as notebooklm-mcp-cli 0.9.14, via uv, uvx, pip or pipx; the MCP entry point is notebooklm-mcp. nlm setup add <tool> writes the config for Claude Code, Claude Desktop, Gemini, GitHub Copilot, Cursor, Cline and Antigravity, or emits JSON for anything else. Claude Desktop users can double-click the .mcpb extension instead. Tested on Pro/free and Google AI Ultra tiers; Enterprise accounts are untested.

Setup effort

Follow the published steps — uv tool install notebooklm-mcp-cli

See installation options

USE CASES

01

Building a research notebook without clicking through the UI

Create it, add the URLs, files and Drive documents as sources, then ask your first question — the exchange shows up in the web UI afterwards.

notebook_createsource_addnotebook_query

02

Turning a body of sources into something you can listen to or show

Generate the studio content from the notebook, revise the slide deck if it needs work, then download the artifact.

studio_createstudio_revisedownload_artifact

03

Asking one question across several notebooks

Run a cross-notebook query instead of repeating yourself in each one, and use tags to choose which notebooks are in scope.

cross_notebook_querytag

04

Repeating a multi-step workflow

Define it as a pipeline and run it, or use batch operations to query, create or delete across many notebooks in one go.

pipelinebatch

05

Getting your work out

Export chat sessions and download every artifact across one notebook or all of them into a local directory.

chat_exportdownload_all_artifacts

43 tools

Listed in project docs. Your client may show a different list.

`notebook_list`

List all notebooks

BEFORE YOU INSTALL

What to know first

Tools you get

43 tools named in the project's documentation.

Requires

uv (or pip / pipx) to install the notebooklm-mcp-cli package from PyPI
A Google account with Gemini Notebook, signed in through nlm login (browser cookies)

INSTALLATION

Connect your client

Server setup

TERMINAL

uv tool install notebooklm-mcp-cli
nlm login

Log in to Google in the browser window nlm login opens; the cookies are extracted automatically (nlm login --check shows whether you are signed in).

TERMINAL

nlm setup add claude-code

For another client, use claude-desktop, gemini, github-copilot, cursor or windsurf instead of claude-code, or run nlm setup add json to generate the entry for any other tool. The manual entries are in the client tabs below.