Appointment Scheduler MCP Server
Enables scheduling and managing appointments through a PostgreSQL database, allowing users to create appointments with name, identification, phone number, and date information via natural language interactions.
README
Appointment Scheduler MCP Server
A Model Context Protocol (MCP) server that connects to a PostgreSQL database to manage appointment scheduling. Built with FastMCP, SQLAlchemy, and Alembic for database migrations.
🚀 Features
- Database Integration: PostgreSQL database with SQLAlchemy ORM
- MCP Protocol: Supports both stdio and HTTP transport modes
- Database Migrations: Alembic for schema management and migrations
- Appointment Management: Schedule appointments with validation
- Docker Support: Containerized deployment with Docker Compose
- Environment Configuration: Secure credential management with .env files
📋 Prerequisites
- Python 3.13+
- PostgreSQL database
- uv package manager (recommended) or pip
🛠️ Installation
Using uv (Recommended)
# Clone the repository
git clone https://github.com/Juan-Andres-Motta/backend-mcp.git
cd backend-mcp
# Install dependencies
uv sync
Using pip
# Clone the repository
git clone https://github.com/Juan-Andres-Motta/backend-mcp.git
cd backend-mcp
# Create virtual environment
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
⚙️ Configuration
Environment Variables
Create a .env file in the project root:
# Database Configuration
DB_HOST=localhost
DB_PORT=5432
DB_NAME=your_database_name
DB_USER=your_username
DB_PASSWORD=your_password
# Database URL (constructed from above)
DATABASE_URL=postgresql://${DB_USER}:${DB_PASSWORD}@${DB_HOST}:${DB_PORT}/${DB_NAME}
# MCP Server Configuration
MCP_TRANSPORT=stdio # Options: stdio, http
MCP_HOST=0.0.0.0 # Only used for HTTP transport
MCP_PORT=8000 # Only used for HTTP transport
Database Setup
-
Using Docker Compose (Recommended):
docker-compose up -d postgres -
Manual PostgreSQL Setup:
- Install PostgreSQL
- Create a database
- Update
.envwith your database credentials
Database Migrations
Run database migrations to create the appointments table:
# Using uv
uv run alembic upgrade head
# Using pip
alembic upgrade head
🚀 Running the Server
Development Mode (stdio)
# Using uv
uv run python main.py
# Using pip
python main.py
HTTP Mode
Set MCP_TRANSPORT=http in your .env file:
# Using uv
uv run python main.py
# Using pip
python main.py
The server will be available at http://localhost:8000
Docker Deployment
# Build and run with Docker Compose
docker-compose up --build
# Run only the MCP server (requires external PostgreSQL)
docker build -t appointment-mcp .
docker run --env-file .env appointment-mcp
📖 API Usage
MCP Tool: schedule_appointment
Schedules a new appointment in the database.
Parameters:
name(string): Full name of the person scheduling the appointmentidentification_number(string): Identification number (ID card, passport, etc.)phone(string): Phone numberdate(string): Appointment date and time in ISO format (YYYY-MM-DDTHH:MM:SS)
Example:
{
"name": "John Doe",
"identification_number": "123456789",
"phone": "+1234567890",
"date": "2024-12-25T14:30:00"
}
Response:
{
"result": "Success: Appointment scheduled for John Doe on 2024-12-25 14:30:00 (ID: 1)"
}
🏗️ Project Structure
backend-mcp/
├── main.py # Main MCP server application
├── pyproject.toml # Project dependencies and configuration
├── uv.lock # uv lock file
├── alembic/ # Database migration files
│ ├── env.py
│ ├── script.py.mako
│ └── versions/
├── .env # Environment variables (create this)
├── .env.example # Environment variables template
├── Dockerfile # Docker container configuration
├── docker-compose.yml # Docker Compose configuration
├── .dockerignore # Docker ignore file
├── .gitignore # Git ignore file
└── README.md # This file
🔧 Development
Running Tests
# Install development dependencies
uv sync --dev
# Run tests
uv run pytest
Database Schema
The appointments table structure:
CREATE TABLE appointments (
id SERIAL PRIMARY KEY,
name VARCHAR(255) NOT NULL,
identification_number VARCHAR(50) NOT NULL,
phone VARCHAR(20) NOT NULL,
date TIMESTAMP NOT NULL
);
Adding New Features
- Define new MCP tools in
main.py - Update database models if needed
- Create Alembic migrations for schema changes
- Update this README
🤝 Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🆘 Troubleshooting
Common Issues
-
Database Connection Error
- Check your
.envfile configuration - Ensure PostgreSQL is running
- Verify database credentials
- Check your
-
Migration Errors
- Run
alembic currentto check migration status - Run
alembic upgrade headto apply pending migrations
- Run
-
MCP Transport Issues
- For stdio mode: Ensure the MCP client supports stdio transport
- For HTTP mode: Check that the port is not in use
Getting Help
- Check the FastMCP documentation
- Review SQLAlchemy documentation
- Check Alembic documentation
📊 Version History
- v1.0.0: Initial release with basic appointment scheduling functionality
- Database integration with PostgreSQL
- Docker containerization
- MCP protocol support (stdio and HTTP)
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。