Marketplace for trusted AI agent skills

Skill Detail

Automate NotebookLM Studio generation and cited research batches with notebooklm-mcp

Use NotebookLM through MCP or a local REST API to run cited Q&A, generate Studio artifacts, and manage high-volume research batches.

Research & ScrapingMCP
Research & Scraping MCP Security Reviewed
⭐ 161 GitHub stars ⬇ 3.5k/wk npm
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill automate-notebooklm-studio-generation-and-cited-research-batches-with-notebooklm-mcp Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
View source Documentation
At a glance
Tools required
Node.js >=18, @roomi-fields/notebooklm-mcp, MCP client or local HTTP REST API, Google NotebookLM/Gemini Notebook account
Install & setup
For REST mode, clone https://github.com/roomi-fields/notebooklm-mcp, run npm install && npm run build, run npm run setup-auth once in a terminal, then start the API with npm run start:http. For MCP mode, build the same package and register dist/index.js with the MCP client, for example claude mcp add notebooklm node /path/to/notebooklm-mcp/dist/index.js. The project also publishes @roomi-fields/notebooklm-mcp on npm.
Author
Romain Peyrichou
Publisher
Individual
Last updated
Aug 21, 2026
Quick brief

Use notebooklm-mcp when an agent needs to operate NotebookLM/Gemini Notebook as a repeatable research engine: add or query notebook sources, run citation-backed Q&A, generate Studio artifacts such as audio, video, reports, presentations, data tables, quizzes, flashcards, and mind maps, or route large batches through multiple Google accounts. Invoke this instead of using NotebookLM normally when the work is an automated agent or operator workflow that needs structured MCP or HTTP calls, reproducible outputs, citation metadata, queue-aware batching, or integration with Claude Code, Cursor, Codex, n8n, Zapier, Make, or cron jobs. The boundary is NotebookLM research and artifact automation through this MCP/REST surface; it is not a generic Google product card, general MCP server listing, or broad automation framework.

How it works

What this skill actually does

Inputs and prerequisites: Node.js >=18, @roomi-fields/notebooklm-mcp, MCP client or local HTTP REST API, Google NotebookLM/Gemini Notebook account.

Setup notes: For REST mode, clone https://github.com/roomi-fields/notebooklm-mcp, run npm install && npm run build, run npm run setup-auth once in a terminal, then start the API with npm run start:http. For MCP mode, build the same package and register dist/index.js with the MCP client, for example claude mcp add notebooklm node /path/to/notebooklm-mcp/dist/index.js. The project also publishes @roomi-fields/notebooklm-mcp on npm.

Source and verification boundary: use https://roomi-fields.github.io/notebooklm-mcp/notebooklm-rest-api as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a MCP workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.