notebooklm-mcp-cli
Unified CLI and MCP server for Google NotebookLM
Decision gist · record as of 2026-08-14
Yes. The package is actively maintained (released 1 day ago), has low install friction, carries no known vulnerabilities, and uses a permissive MIT license. It fills a genuine gap for programmatic Gemini Notebook access. The main caveat is that it relies on undocumented internal APIs that may break without notice—suitable for personal automation and experimentation, but use with caution in production workflows where API stability is critical.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.11 or later.
- Authentication requires extracting cookies from your browser session with Gemini Notebook; the package provides tooling for this but it is a manual setup step.
- Low friction install with a pure-Python wheel and active maintenance—released 1 day ago with 5852 GitHub stars.
License · maintenance · safety
MIT (permissive) — MIT license (permissive) means you can use, modify, and distribute this package freely with minimal restrictions, making it suitable for both personal and commercial projects.
last release 2026-08-13 (1 days) · last repo commit 2026-08-13 · 5,852 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 119,567 downloads/mo, #12,065 on PyPI
Alternatives
Verify before relying
pip install notebooklm-mcp-cli
nlm notebook list
nlm notebook create "My Research"
nlm source add --url "https://example.com"
nlm studio create audio- Whether all Gemini Notebook features are fully supported or if some remain untested (description notes testing with Pro/free and Ultra tiers, but Enterprise support is unverified).
- Stability guarantees for internal API usage—the package relies on undocumented Gemini Notebook APIs that may change without notice.
- Whether the MCP server works reliably with all advertised AI tools (Claude, Gemini, Cursor, GitHub Copilot, Cline) or if some integrations have known limitations.
What it is and what it does
notebooklm-mcp-cli is a unified command-line interface and Model Context Protocol server that bridges your terminal and AI agents to Google Gemini Notebook. It lets you programmatically create notebooks, add sources (URLs, files, Google Drive), generate podcasts and other studio content, query notebooks, manage chat sessions, and download artifacts—all from the CLI or by connecting AI assistants like Claude or Cursor as MCP clients.
The package wraps Gemini Notebook's internal APIs (which are undocumented and subject to change) and provides two entry points: the `nlm` CLI for direct terminal use and scripting, and the `notebooklm-mcp` server for AI agents to call as tools. It supports batch operations, cross-notebook queries, pipelines for multi-step workflows, and tagging. Setup is straightforward for Claude Desktop (one-click `.mcpb` extension) or manual for other tools via JSON config generation.
Use it for
- Automate research workflows: create notebooks, add sources, and generate podcasts or summaries without manual UI interaction.
- Integrate Gemini Notebook into AI agent workflows: connect Claude, Cursor, or other MCP-compatible tools to let them manage notebooks on your behalf.
- Batch process multiple notebooks: query, create, or delete notebooks in bulk via CLI commands or pipeline definitions.
- Download and archive artifacts: export all generated content (audio, slides, videos) from one or many notebooks to local storage.
- Extend CI/CD pipelines: trigger notebook creation and content generation as part of automated research or documentation workflows.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
The package is actively maintained (released 1 day ago), has low install friction, carries no known vulnerabilities, and uses a permissive MIT license. It fills a genuine gap for programmatic Gemini Notebook access. The main caveat is that it relies on undocumented internal APIs that may break without notice—suitable for personal automation and experimentation, but use with caution in production workflows where API stability is critical.
Install
notebooklm-mcp-cli on PyPI
Before you install
Low friction install with a pure-Python wheel and active maintenance—released 1 day ago with 5852 GitHub stars. Nine runtime dependencies are all common, well-maintained packages (fastmcp, httpx, pydantic, typer, etc.), suggesting a stable dependency footprint.
Requires Python 3.11 or later. Authentication requires extracting cookies from your browser session with Gemini Notebook; the package provides tooling for this but it is a manual setup step.
License in practice
MIT license (permissive) means you can use, modify, and distribute this package freely with minimal restrictions, making it suitable for both personal and commercial projects.
Quickstart
pip install notebooklm-mcp-cli
nlm notebook list
nlm notebook create "My Research"
nlm source add --url "https://example.com"
nlm studio create audioVerify before relying
- Whether all Gemini Notebook features are fully supported or if some remain untested (description notes testing with Pro/free and Ultra tiers, but Enterprise support is unverified).
- Stability guarantees for internal API usage—the package relies on undocumented Gemini Notebook APIs that may change without notice.
- Whether the MCP server works reliably with all advertised AI tools (Claude, Gemini, Cursor, GitHub Copilot, Cline) or if some integrations have known limitations.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.11 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 9 packagesfastmcphttpxplatformdirspydanticpyyamlrichtypertyping-extensionswebsocket-client |
| Maintenance | Actively maintained 1 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 119,567 / month, #12,065 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaEnvironment :: ConsoleIntended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13 |
Evidence: notebooklm_mcp_cli-0.9.11-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “gemini notebook cli”
- notebooklm-mcp-cliProvides CLI and MCP server access to Google Gemini Notebook…
- notebooklm-pyProgrammatic access to Google Gemini Notebook for automating…
- google-agents-cliA CLI toolchain that equips coding agents (Claude Code, Antigravity…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also analytics-mcp · notebooklm-py · google-agents-cli · jupyter-mcp-server · astro-airflow-mcp · nextcloud-mcp-server · blender-mcp · mcp-server-appwrite · workspace-mcp · flights