Interfaces with Google NotebookLM to enable autonomous academic research, knowledge management, and the generation of research artifacts like audio overviews and reports.
Allows for the generation of research data tables directly within Google Sheets.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@KHU Notebook Research Assistant Conduct deep research on renewable energy and generate a research report"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Version: 0.0.1 (2026-01-31)
Author: Taekyung Kim, PhD. Professor, Kyung Hee University
The KHU Notebook Research Assistant is a specialized Model Context Protocol (MCP) server designed to interface with Google NotebookLM. It empowers AI agents to conduct autonomous academic research, manage knowledge bases, and generate study artifacts efficiently.
This project is tailored for research and educational purposes, enabling seamless integration between LLMs and NotebookLM's grounded reasoning capabilities.
Related MCP server: Gemini Research MCP Server
Autonomous Deep Research: Performs multi-step web research and automatically summarizes and imports findings into your notebook.
Study Artifact Generation: Instantly creates derived materials from your sources:
Audio Overviews (Podcasts)
Research Reports
Infographics
Presentation Slides
Data Tables (Google Sheets)
Flashcards & Quizzes
Mind Maps
Knowledge Management: Systematic control over notebook creation, source addition (URLs, Text, PDFs), and organization.
npm install
npm run buildThis server requires a valid Google session to interact with NotebookLM.
Session credentials (cookies) should be stored in ~/.notebooklm-mcp/auth.json or passed via environment variables.
Tool | Description |
| Lists all active research notebooks. |
| Conducts deep web research on a specific topic. |
| Generates artifacts like Slides, Reports, or Audio. |
| Injects new research materials (URLs, Text) into the notebook. |
Private / Academic Use Only. Copyright (c) 2026 Taekyung Kim, PhD. All Rights Reserved.
Add a specific source (text, url, pdf) to the notebook.
Inputs: notebook_id (required), category (required), payload (required), title.
Generate various study materials and artifacts.
Inputs: notebook_id (required), material_type (required), context.
Conduct deep web research and import findings automatically.
Inputs: notebook_id (required), topic (required).
Create a new research notebook.
Inputs: title (required).
List all available research notebooks.
Inputs: no named parameters.
Update session cookies manually.
Inputs: cookies (required), csrf_token.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 6 tools
Most tools have distinct purposes: notebook creation/listing, content addition, research, and credential updates. However, 'generate_study_material' and 'research_deep_search' could overlap if study materials involve research findings, though descriptions suggest different focuses (generation vs. search/import).
Naming is mixed: 'research_notebook_create' and 'research_notebook_list' follow a consistent pattern, but 'add_source_content' and 'generate_study_material' use different verb styles, and 'research_deep_search' and 'update_credentials' deviate further. The set lacks a uniform convention, though names remain readable.
With 6 tools, the count is reasonable for a research assistant server, covering core notebook management and research tasks. It's slightly lean but not insufficient, as each tool appears to serve a specific function without obvious bloat.
The toolset covers notebook creation, listing, and content addition, but lacks update or delete operations for notebooks or sources, which could limit agent workflows. Research and generation tools are included, but gaps in lifecycle management may cause dead ends in complex tasks.
One MCP server for all web data. Scrape, search, crawl, and AI research in one install.
Academic research MCP server for paper search, citation checks, graphs, and deep research.
Markdown-based note-taking with a hosted MCP server. Your notes serve you and your AI.
An MCP server for deep research or task groups
