AI-Notion Integration MCP Server
Enables AI assistants to save and manage question-and-answer pairs within a structured Notion database. It provides tools for database setup, entry creation, and querying existing conversation history.
README
Notion MCP Server
AI-powered knowledge management with Notion integration and spaced repetition learning system.
✨ Features
- 📝 Auto-save conversations - Save AI Q&A to Notion with intelligent categorization
- 🔍 Advanced search - Query by date, category, tags, and full-text search
- 🧠 Spaced repetition - Science-based review scheduling (1/2/4/7/15 days)
- 📊 Progress tracking - Track mastery levels (⭐-⭐⭐⭐⭐⭐) and review counts
📦 Installation
Option 1: NPM (Recommended)
npm install -g @itsyuimorii/notion-mcp-server
Option 2: From Source
git clone https://github.com/itsyuimorii/notion-mcp-server.git
cd notion-mcp-server
npm install
npm run build
🚀 Quick Start
1. Create Notion Integration
- Go to Notion Integrations and create a new integration

- Give your integration a name (e.g., "AI Learning Tracker") and select the appropriate capabilities (read & write)
- Copy the "Internal Integration Token" and paste it into your
.envfile

- Share your Notion page with the integration
2. Configure Environment
Create a .env file:
NOTION_API_TOKEN=ntn_your_token_here
NOTION_PARENT_PAGE_ID=your_page_id_here
NOTION_DATABASE_ID=your_database_id_here # Optional
3. Configure Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"notion-mcp-server": {
"command": "node",
"args": ["/path/to/notion-mcp-server/dist/index.js"],
"env": {
"NOTION_API_TOKEN": "ntn_your_token",
"NOTION_PARENT_PAGE_ID": "your_page_id",
"NOTION_DATABASE_ID": "your_database_id"
}
}
}
}
4. Restart Claude Desktop
You're ready to use it!
🛠️ Available Tools
| Tool | Description |
|---|---|
notion_setup_database |
Create pre-configured database with spaced repetition fields |
notion_ai_save_entry |
Save Q&A with auto-categorization and tags |
notion_query_database |
Search with filters (date/category/tags) |
notion_check_reviews |
Check overdue and upcoming reviews |
notion_update_mastery |
Update mastery level and schedule next review |
📁 Project Structure
notion-mcp-server/
├── src/
│ ├── index.ts # Main MCP server
│ ├── config.ts # Configuration
│ └── types.ts # TypeScript types
├── docs/
│ └── images/ # Documentation images
├── QUICKSTART.md # Detailed setup guide
├── DEMO_SCENARIOS.md # Usage examples
├── LICENSE # MIT License
└── package.json # Dependencies
📚 Documentation
- QUICKSTART.md - Complete setup guide
- DEMO_SCENARIOS.md - Real-world usage examples
🔧 Requirements
- Node.js 18+
- npm 9+
- Notion account with workspace
- Claude Desktop (latest version)
🐛 Troubleshooting
Connection failed?
- Check
.envfile has correct token - Run
npm run buildto generatedist/index.js - Verify path in Claude config
- Restart Claude Desktop
Database permission denied?
- Go to your Notion page
- Click "..." → "Add connections"
- Select your integration
- Restart Claude Desktop
📄 License
MIT - see LICENSE
🔗 Links
New to this project? Start with QUICKSTART.md 🚀
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。