KHU Notebook Research Assistant
# KHU Notebook Research Assistant (MCP)
**Version:** 0.0.1 (2026-01-31)
**Author:** Taekyung Kim, PhD. Professor, Kyung Hee University
## Overview
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.
## Key Capabilities
* **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.
## Installation
```bash
npm install
npm run build
```
## Configuration
This 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.
## Tools Available
| Tool | Description |
|------|-------------|
| `research_notebook_list` | Lists all active research notebooks. |
| `research_deep_search` | Conducts deep web research on a specific topic. |
| `generate_study_material` | Generates artifacts like Slides, Reports, or Audio. |
| `add_source_content` | Injects new research materials (URLs, Text) into the notebook. |
## License
Private / Academic Use Only.
Copyright (c) 2026 Taekyung Kim, PhD. All Rights Reserved.
TDQS
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.