Azure Container Apps - AI & MCP Playground

What is Azure Container Apps - AI & MCP Playground?

This project showcases how to use the MCP protocol with Azure OpenAI, providing a simple demo terminal application that interacts with a TODO list Agent.

How to use Azure Container Apps - AI & MCP Playground?

To use this project, clone the repository, install the dependencies, and run the MCP servers either in Docker or outside of Docker. You can then interact with the LLM agent through the MCP host terminal.

Key features of Azure Container Apps - AI & MCP Playground?

• Supports both HTTP and SSE (Server-Sent Events) protocols.
• Provides a terminal interface for user interaction with the agent.
• Integrates with multiple LLM providers including Azure OpenAI, OpenAI, and GitHub Models.
• Utilizes a Postgres database to store the state of the agent and tools.

Use cases of Azure Container Apps - AI & MCP Playground?

1. Managing a TODO list through an AI agent.
2. Interacting with various LLMs for different tasks.
3. Demonstrating the capabilities of the MCP protocol in a practical application.

FAQ from Azure Container Apps - AI & MCP Playground?

• What are the prerequisites to run this project?

You need Node.js, npm, Docker, and an OpenAI compatible endpoint.

• Can I run the MCP servers without Docker?

Yes, you can run the servers outside of Docker by starting them in separate terminals.

• What LLM providers are supported?

The project supports Azure OpenAI, OpenAI, and GitHub Models.