MCP Server Project

Multi-Server MCP (Model Context Protocol) implementation providing weather information and temperature conversion services with LangChain/LangGraph integration.

Features

• Weather Service: Real-time weather data via OpenWeatherMap API with comprehensive meteorological information
• Temperature Converter: Temperature conversion between Celsius, Fahrenheit, and Kelvin units
• LangChain/LangGraph Integration: Advanced AI-powered chat client with intelligent tool usage
• Automated Startup: One-command deployment with automatic server management
• FastMCP Servers: MCP servers with HTTP transport

Project Structure

mcp_servers/
├── weather/
│   ├── server.py              # Weather MCP server
│   └── tools/
│       └── weather_provider.py   # Weather service implementation
├── temperature/
│   ├── server.py              # Temperature MCP server
│   └── tools/
│       └── temperature_converter.py  # Temperature conversion service
├── chat_client.py             # MCP chat client with LangChain integration
├── start.sh                   # Automated startup script
├── pyproject.toml            # Poetry configuration and dependencies
└── README.md                 # Project documentation

Installation

Prerequisites

• Python 3.11+
• Poetry (recommended) or pip
• OpenWeatherMap API key
• DeepSeek API key

Setup

1. Clone the repository:

git clone <repository-url>
cd MCP_server

2. Install dependencies:

# Using Poetry (recommended)
poetry install

3. Configure environment variables: Create a .env file with the following variables:

# OpenWeatherMap API
OPENWEATHER_API_KEY=your_openweather_api_key

# LLM Configuration (for LangChain client)
DEEPSEEK_API_KEY=your_deepseek_api_key
OPENROUTER_BASE_URL=https://openrouter.ai/api/v1

Usage

Quick Start (Recommended)

Use the provided startup script to run everything in one command:

chmod +x start.sh
./start.sh

This script will:

1. Start the weather server on port 8000
2. Start the temperature server on port 9000
3. Wait for servers to initialize (2 seconds)
4. Launch the chat client
5. Automatically cleanup servers when chat ends

Manual Setup

If you prefer to start servers manually:

1. Weather Server (Port 8000):

poetry run python mcp_servers/weather/server.py

2. Temperature Server (Port 9000):

poetry run python mcp_servers/temperature/server.py

3. Chat Client:

poetry run python chat_client.py

Weather Service

Endpoint: http://127.0.0.1:8000/mcp

Available Tool: get_weather

Parameters:

• city (str): City name (e.g., "London", "New York")
• units (str, optional): Temperature units - "metric", "imperial", or "kelvin" (default: "metric")

Example Response:

{
  "success": true,
  "city": "London",
  "country": "GB",
  "temperature": {
    "current": 15.2,
    "feels_like": 14.1,
    "min": 12.3,
    "max": 17.8,
    "unit": "°C"
  },
  "weather": {
    "main": "Clouds",
    "description": "overcast clouds",
    "icon": "04d"
  },
  "wind": {
    "speed": 3.5,
    "direction_degrees": 220,
    "direction_name": "SW",
    "unit": "m/s"
  },
  "humidity": 73,
  "pressure": {
    "value": 1013,
    "unit": "hPa"
  },
  "coordinates": {
    "latitude": 51.5074,
    "longitude": -0.1278
  }
}

Temperature Conversion Service

Endpoint: http://127.0.0.1:9000/mcp

Available Tool: convert_temperature

Parameters:

• temperature (float): Temperature value to convert
• from_unit (str): Source unit ("celsius", "fahrenheit", "c", "f", "k")
• to_unit (str): Target unit ("celsius", "fahrenheit", "c", "f", "k")

Example Response:

{
  "success": true,
  "original_temperature": 25.0,
  "original_unit": "celsius",
  "converted_temperature": 77.0,
  "converted_unit": "fahrenheit",
  "conversion_formula": "°F = (°C × 9/5) + 32"
}

Features in Detail

Weather Provider

• Multiple Units: Supports metric, imperial, and kelvin units
• Comprehensive Data: Temperature, humidity, pressure, wind, visibility
• Validation: Input validation

Temperature Converter

• Multiple Formats: Supports full names and abbreviations
• Validation: Temperature validation against absolute zero
• Precision: Proper rounding and precision handling
• Formulas: Returns conversion formulas for transparency

Chat Clients

• Basic Client: Simple MCP integration
• LangChain Client: Advanced AI-powered conversations
• Error Handling: Comprehensive error handling and recovery
• Session Management: Chat history tracking

Configuration

Server Ports

• Weather Service: 8000
• Temperature Service: 9000

Error Handling

The project implements comprehensive error handling:

• Validation Errors: Input validation with helpful error messages
• Logging: Structured logging for debugging and monitoring

Security Considerations

• API keys are loaded from environment variables