Azure Openai MCP Example

🚀 Azure Container Apps AI MCP Project

This is an AI-related project about Azure Container Apps, mainly focusing on the development and integration of intelligent services in a containerized environment. Here's a detailed description of the project:

🚀 Quick Start

📦 Installation

Environment Variable Setup

To ensure the project runs smoothly, you need to set the following environment variables in the .env file:

Using Azure OpenAI without Key Authentication

If you're using the key - less authentication feature of Azure OpenAI, make sure to provide the following information:

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

# (Optional) If you need to use API key authentication, you can set the following variable:
# AZURE_OPENAI_API_KEY=your_azure_openai_api_key

Also, ensure that you've logged in to your Azure account via the Azure CLI and selected the target subscription:

az login

Using OpenAI Service

To use the OpenAI API, set the following variables:

OPENAI_API_KEY=your_openai_api_key
MODEL="gpt-4.1"

Using GitHub Models

To use the models provided by GitHub, set the following variables:

GITHUB_TOKEN=your_github_token
MODEL="openai/gpt-4.1"

💻 Usage Examples

Running in DevContainer (Recommended)

This project provides a DevContainer configuration, allowing you to run the project in a containerized environment. This is the recommended way to run the project as it ensures all dependencies are correctly installed and configured.

After opening the project in DevContainer, follow the instructions in the Docker section to run the MCP server.

Running in Docker

You can use the provided Docker Compose file to run the MCP server using Docker containers. This method is suitable for testing and development environments. The steps are as follows:

1. Make sure Docker and Docker Compose are installed on your machine. Enter the docker compose command in the terminal to check if they are installed.
2. In the project root directory, run the following command to build and start the containers:

docker compose up -d --build

This command will build and start the HTTP and SSE MCP servers, as well as the PostgreSQL database container. 3. Use the following command to access the MCP host terminal:

docker exec -it mcp-host bash

4. Inside the container, run the MCP host and interact with the LLM agent. Refer to the usage instructions section for specific steps.

Running without Docker

If you're not running in a Docker environment, refer to the specific project documentation or guide to learn how to deploy and configure the service in a traditional environment.

✨ Features

The project's features include but are not limited to the intelligent management of containerized services, model integration, and interaction. Here's an overview of the main features:

• Container Orchestration: Automate the deployment and scaling of container applications through Kubernetes or other orchestration tools.
• Intelligent Service Integration: Combine AI models with container applications to provide intelligent service capabilities.
• Monitoring and Logging: Integrate container runtime monitoring and log management functions for easy maintenance and optimization.

⚠️ Important Note

• When using key - less authentication, ensure that your Azure account has the relevant features enabled and the access policies are correctly configured.
• When using GitHub models, comply with the usage limits and specifications of its API.
• Before deploying in a production environment, conduct comprehensive testing and optimization to ensure the stability and reliability of the service.

📄 License

Please check the project's LICENSE file for specific terms and conditions of use.

🤝 Contribution Guidelines

If you wish to contribute to this project, refer to the CONTRIBUTING.md file for detailed information.

The above is the main content of the project. For further information or if you encounter any issues, refer to the relevant documentation or contact the project maintainers.