Azure Container Apps Ai MCP

🚀 Azure Container Apps AI MCP Project Guide

This project aims to demonstrate how to use Azure containers and AI technologies to build an efficient microservices architecture. Through this project, you'll learn how to configure and manage cloud containers while integrating artificial intelligence models to enhance application functionality.

🚀 Quick Start

✨ Features

• Showcase the construction of an efficient microservices architecture using Azure containers and AI technologies.
• Enable users to learn cloud container configuration and management.
• Integrate AI models to enhance application features.

📦 Installation

Environment Requirements

• Operating System: Supports Linux, Windows, or macOS.
• Development Tools: Node.js and npm (version 14.0+) need to be installed.
• Virtualization Technology: It is recommended to use Docker and Docker Compose for containerized deployment.
• Cloud Service: Testing and deployment on Azure Cloud are recommended.

Project Configuration

Configuration File Explanation

The root directory of the project contains an env file for storing environment variables. The following are the key variables that need to be set:

# Azure OpenAI settings
AZURE_OPENAI_ENDPOINT="https://<ai-foundry-openai-project>.openai.azure.com"
MODEL="gpt-4.1"

# Optional: Use API key for authentication
AZURE_OPENAI_API_KEY=your_azure_openai_api_key

# OpenAI settings
OPENAI_API_KEY=your_openai_api_key
MODEL="gpt-4.1"

# GitHub model settings
GITHUB_TOKEN=your_github_token
MODEL="openai/gpt-4.1"

Notes

• Azure OpenAI: Using Managed Identity requires configuration in the Azure Cloud environment. For local development, it is recommended to use an API key for authentication.
• OpenAI: You must set OPENAI_API_KEY to call OpenAI's API services properly.
• GitHub Model: A valid GITHUB_TOKEN is required to call GitHub's AI model.

💻 Usage Examples

Basic Usage

Using DevContainer (Recommended)

The project has integrated DevContainer configuration, which facilitates running in a containerized environment. This method is the best choice for running the project as it automatically handles the installation and configuration of all dependencies.

After running the project in the DevContainer environment, refer to the Docker section for the next steps.

Using Docker

1. Build and Start Containers In the project root directory, execute the following command:

   docker compose up -d --build
   

   This command will build and start two MCP servers (HTTP and SSE) and a PostgreSQL database container.
2. Access the MCP Host Terminal Execute the following command to enter the interactive environment of the MCP host:

   docker exec -it mcp-host bash
   

3. Start the Service In the MCP host, run the following command to start the relevant service:

   npm start mcp-server
   

Running Directly

If you don't use a containerized environment, you can run the project directly locally. Make sure Node.js and npm are installed.

1. Install Dependencies In the project directory, execute:

   npm install
   

2. Start the Application Run the following command to start the service:

   npm start
   

📄 License

This project is licensed under the MIT License. Please refer to the LICENSE file for detailed information.

⚠️ Important Note

• It is recommended to use containerized deployment in a production environment to ensure system stability and scalability.
• When calling AI services, please comply with the corresponding API usage policies and restrictions.
• Regularly update dependencies to ensure project security and compatibility.

By following the above steps, you can successfully configure and run the Azure Container Apps AI MCP project. If you have any questions or suggestions, please feel free to contact the project maintainers.