MCP Server Fag

🚀 Distributed MCP Server

A Model Context Protocol (MCP) server that provides legal information query, weather data, Azure pricing, and utility function tools.

🚀 Quick Start

This server offers API tools for Microsoft Copilot or other AI assistants supporting the MCP protocol.

✨ Features

Legal Information Tools

• Get Article Information: Query Chinese criminal law articles by barcode.
• Content Search: Find relevant criminal law articles by keywords.
• Article Name Query: Search for legal information by article or crime name.
• Specific Paragraph Retrieval: Get specific paragraphs of an article.
• Get Full Text Content: Obtain the full text of the Chinese criminal law.

Weather and Utility Tools

• Weather Alerts: Get weather alerts at the US state level.
• Weather Forecast: Query weather forecasts by latitude and longitude.
• Azure Price Query: Query Azure service prices using OData filters.
• Chinese Character Count: Count the number of Chinese characters in the text.

🔧 Technical Details

The MCP server is based on the following technologies:

- FastMCP framework
- MongoDB database
- Azure OpenAI service

📦 Installation

1. Clone the project repository.
2. Install dependencies: pip install -r requirements.txt.
3. Configure environment variables, including the MongoDB connection string and Azure OpenAI API key.
4. Start the server: python app.py.

💻 Usage Examples

Basic Usage

# Example: Use the legal information tool
curl http://localhost:5000/api/legal -X POST -H "Content-Type: application/json" -d '{"query": "盗窃罪"}'

# Example: Query the weather forecast
curl http://localhost:5000/api/weather -X POST -H "Content-Type: application/json" -d '{"latitude": 34.0522, "longitude": -118.2437}'

Docker Deployment

# Build the image
docker build -t mcp-server .

# Run the container
docker run -p 5000:5000 --env MONGO_URI=<<Your MongoDB connection string>> --env AZURE_OPENAI_KEY=<<Your Azure OpenAI key>> mcp-server

Azure Deployment Options

Using Kubernetes Service Extension

# Example YAML configuration
apiVersion: apps/v1beta2
kind: Deployment
metadata:
  name: mcp-server-deployment
spec:
  replicas: 3
  selector:
    matchLabels:
      app: mcp-server
  template:
    metadata:
      labels:
        app: mcp-server
    spec:
      containers:
      - name: mcp-server
        image: mcr.microsoft.com/mcp/server:v1.0.0
        ports:
        - containerPort: 5000

Using Azure Function Extension

// Example JavaScript code
module.exports = async function (context, req) {
    context.log('Get weather forecast request');
    const weatherData = await getWeather(req.query.latitude, req.query.longitude);
    context.res.json(weatherData);
};

📚 Documentation

• Model Context Protocol
• FastMCP Framework
• Azure Container Apps
• Azure Functions
• Azure Cosmos DB