KHU Notebook Research Assistant
An MCP server that interfaces with Google NotebookLM to enable autonomous academic research and systematic knowledge management. It allows users to perform deep web searches and automatically generate study artifacts like research reports, presentation slides, and audio overviews.
README
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
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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。