roomi-fields/notebooklm-mcp — Google NotebookLM over MCP + a local HTTP REST API.

Description and use

**Summary**
roomi‑fields/notebooklm-mcp is an open‑source bridge that runs Google NotebookLM on the Model‑Context‑Protocol (MCP) and exposes a local HTTP REST API. It adds citation‑backed Q&A, audio/video/content generation, and multi‑account rotation, making it easy to plug NotebookLM into automation platforms such as Claude Code, Codex, Cursor, n8n, Zapier, and Make.

**Value**
The project turns a powerful generative AI (NotebookLM) into a standards‑based service that can be called from any MCP‑compatible agent. By providing a REST endpoint and built‑in support for citations, media creation, and account switching, it lets developers and ops teams connect AI assistants to real‑world tools and data without writing custom wrappers for each platform.

**Practical adoption path**

1. **Spin‑up** – Clone the repo, run npm install && npm start (or use the provided Docker image) to launch the local NotebookLM MCP server.
2. **Configure** – Add your Google credentials and, if needed, multiple NotebookLM accounts in the .env file to enable rotation.
3. **Integrate** – Point any MCP‑aware component (Claude Code, Codex, n8n, Zapier, Make, etc.) to the server’s HTTP endpoint; the SDK/CLI shipped with the repo simplifies request construction and response parsing.
4. **Extend** – Use the TypeScript SDK or the open API spec to add custom handlers (e.g., trigger audio/video generation or enforce citation policies) and then deploy the service behind a reverse proxy for internal or SaaS use.

**Production readiness**
The repository shows strong signals for a pilot‑grade deployment: recent commits (last updated 2026‑05‑14), 75 GitHub stars, active forking, and a TypeScript codebase with clear API documentation. Its modular MCP/REST design aligns with existing automation ecosystems, and the multi‑account rotation mitigates rate‑limit issues in production. While the license, security audit, and long‑term maintainer commitment still require a final check, the overall health and ecosystem adoption make it a viable candidate for production use after standard security hardening.

Problem

roomi-fields/notebooklm-mcp helps connect AI assistants to real tools and data through a standard protocol.

Outcome

High for an OSS candidate: recent activity, adoption, and ecosystem signals are strong enough for a serious pilot.

Workflow

• connect AI agents to tools
• ship Model Context Protocol servers
• standardize integrations

Evidence

Google NotebookLM over MCP + a local HTTP REST API. Citation-backed Q&A, audio/video/content generation, multi-account rotation. For Claude Code, Codex, Cursor, n8n, Zapier, Make.

Source