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)
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.