Todo Assistant with AI and Google Calendar Integration
LocalAbout Todo Assistant with AI and Google Calendar Integration
Todo Assistant with AI and Google Calendar Integration is a web app for managing tasks and calendar events through natural-language chat. It combines OpenAI GPT-3.5 Turbo, Google Calendar, persistent SQLite storage, and an approval workflow for sensitive tools.
Key features
- 01Natural-language todo management
- 02Google Calendar synchronization
- 03English and Turkish support
- 04Approval workflow for sensitive tools
- 05SQLite-based persistent storage
- 06Responsive web interface
Use cases
- 01Add or complete todos by chat
- 02Sync todo items with Google Calendar
- 03Review upcoming calendar events
- 04Approve sensitive tool operations
MCP support
The application provides MCP endpoints for interaction, health checks, and listing available tools. Its MCP support enables standardized AI tool interactions alongside traditional REST endpoints.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMETodo Assistant with AI and Google Calendar Integration
A modern, AI-powered todo list and calendar management application that combines OpenAI's Assistant API with Google Calendar integration. Built with TypeScript and featuring both MCP (Model Context Protocol) and traditional API endpoints.
Todo Assistant Main Screen
Todo Assistant Main Screen
Todo Assistant Main Screen
🌟 Key Features
- AI-Powered Chat Interface: Natural language interaction using OpenAI's GPT-3.5 Turbo
- Smart Todo Management: Add, remove, list, and toggle todos using natural language
- Google Calendar Integration: Seamlessly sync todos with Google Calendar
- Multi-Language Support: Full support for English and Turkish
- Tool Approval System: Secure approval workflow for sensitive operations
- MCP (Model Context Protocol): Standardized AI tool interactions
- Responsive Design: Modern, mobile-friendly web interface
- Persistent Storage: SQLite database for reliable data management
🛠️ Technical Stack
-
Backend:
- Node.js with Express
- TypeScript
- SQLite (via better-sqlite3)
- OpenAI Assistant API
- Google Calendar API
-
Frontend:
- HTML5 & CSS3
- Modern JavaScript
- Responsive Design
-
AI & Integration:
- OpenAI GPT-3.5 Turbo
- Model Context Protocol (MCP)
- OAuth 2.0 for Google Calendar
📋 Prerequisites
- Node.js (v16 or higher)
- npm or yarn
- OpenAI API key
- Google Cloud Console account
- SQLite
🚀 Getting Started
-
Clone the Repository
git clone https://github.com/yourusername/todo-assistant.git cd todo-assistant -
Install Dependencies
npm install -
Environment Setup Create a
.envfile in the root directory:OPENAI_API_KEY=your_openai_api_key PORT=3000 CLIENT_ID=your_google_client_id CLIENT_SECRET=your_google_client_secret GOOGLE_REDIRECT_URI=http://localhost:3000/google/callback -
Build and Run
# Build TypeScript npm run build # Start server npm start # Development mode with auto-reload npm run dev # Start with MCP enabled npm run dev:mcp
🗄️ Database Structure
Todos Table
CREATE TABLE todos (
id INTEGER PRIMARY KEY AUTOINCREMENT,
text TEXT NOT NULL,
completed BOOLEAN NOT NULL DEFAULT 0,
createdAt TEXT NOT NULL
)
Calendar Events Table
CREATE TABLE calendar_events (
id INTEGER PRIMARY KEY AUTOINCREMENT,
todoId INTEGER NOT NULL,
title TEXT NOT NULL,
date TEXT NOT NULL,
time TEXT NOT NULL,
createdAt TEXT NOT NULL,
FOREIGN KEY (todoId) REFERENCES todos(id) ON DELETE CASCADE
)
🔌 API Endpoints
Traditional REST API
POST /api/thread- Create/get user threadPOST /api/chat- Send/receive messagesGET /api/history/:userId- Get chat historyPOST /api/tool-response- Handle tool approvals
MCP Endpoints
POST /mcp- Main MCP interaction endpointGET /mcp/health- Health checkGET /mcp/tools- Available tools listing
💡 Usage Examples
English Commands
"Add 'Buy groceries' to my todo list"
"Show all my todos"
"Mark todo #3 as complete"
"Add 'Team meeting' to calendar for tomorrow at 2pm"
"Show my calendar events for next week"
Turkish Commands
"Alışveriş yapmayı listeye ekle"
"Tüm görevlerimi göster"
"3 numaralı görevi tamamlandı olarak işaretle"
"Yarın saat 14:00'da takım toplantısını takvime ekle"
"Gelecek haftaki takvim etkinliklerimi göster"
🔒 Security Features
- Tool approval workflow for sensitive operations
- OAuth 2.0 authentication for Google Calendar
- Secure credential management
- Input validation and sanitization
🌐 Google Calendar Setup
- Go to Google Cloud Console
- Create a new project or select existing
- Enable Google Calendar API
- Configure OAuth 2.0 credentials:
- Set application type as "Web application"
- Add authorized redirect URI:
http://localhost:3000/google/callback - Download credentials and update
.envfile
🤝 Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
📝 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
- OpenAI for their powerful Assistant API
- Google Calendar API team
- Contributors and testers
📞 Support
For support, please open an issue in the GitHub repository or contact the maintainers.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.