MCP.so
登录

Azure Container Apps - AI & MCP Playground

@manekinekko

关于 Azure Container Apps - AI & MCP Playground

This project showcases how to use the MCP protocol with Azure OpenAI. It provides a simple example to interact with OpenAI's API seamlessly via an MCP server and client.

基本信息

分类

云与基础设施

许可证

MIT

运行时

node

传输方式

stdio

发布者

manekinekko

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "azure-openai-mcp-example": {
      "command": "docker",
      "args": [
        "compose",
        "up",
        "-d",
        "--build"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Azure Container Apps - AI & MCP Playground?

This demo application showcases the MCP protocol with OpenAI, Azure OpenAI, and GitHub Models. It provides a terminal application that interacts with a TODO list agent using tools from an MCP server, intended for developers exploring AI agent integration.

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

Clone the repository and run docker-compose up to start containers. Alternatively, install dependencies with npm install per prefix and run npm start --prefix mcp-server-http, mcp-server-sse, and mcp-host in separate terminals. Configure the LLM provider via a .env file with keys like OPENAI_API_KEY, AZURE_OPENAI_ENDPOINT, or GITHUB_TOKEN.

Key features of Azure Container Apps - AI & MCP Playground

  • Supports SSE and HTTP streaming MCP servers
  • Integrates with OpenAI, Azure OpenAI, GitHub Models
  • Uses DocumentDB Local for state persistence
  • Provides tools for TODO list management
  • Docker Compose for easy setup
  • Configurable debug logging via DEBUG env variable

Use cases of Azure Container Apps - AI & MCP Playground

  • Build a terminal-based AI assistant with tool access
  • Experiment with MCP protocol using different LLM providers
  • Develop and test MCP server implementations
  • Explore integration of AI agents with persistent database storage

FAQ from Azure Container Apps - AI & MCP Playground

How does this server differ from other MCP servers?

This playground focuses on demonstrating MCP with multiple LLM providers and includes both HTTP and SSE transport, a local database, and a host application.

What are the runtime dependencies?

Node.js 22+, Docker, and an OpenAI compatible endpoint (OpenAI API key, GitHub token, or Azure OpenAI endpoint).

Where is agent state stored?

State is stored in DocumentDB Local, a lightweight database running in Docker.

Does it support authentication?

Authentication is a work in progress; currently no token-based auth for the MCP servers.

How can I debug the MCP host?

Set the DEBUG environment variable to mcp:* before starting the host.

评论

云与基础设施 分类下的更多 MCP 服务器