OpenAI MCP Example

@manekinekko

代码仓库

基本信息

分类

AI 与智能体

许可证

MIT

传输方式

stdio

作者

manekinekko

关于 OpenAI MCP Example

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.

#mcp #openai #agents #llm

OpenAI MCP Example 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

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

OpenAI MCP Example 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

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 OpenAI MCP Example?

OpenAI MCP Example is a demo application that showcases the Model Context Protocol (MCP) with OpenAI, Azure OpenAI, and GitHub Models. It provides a terminal-based agent that can perform actions using tools exposed by an MCP server, backed by a DocumentDB Local database.

How to use OpenAI MCP Example?

Run the MCP host after starting the MCP server implementations (HTTP and SSE) and configuring an LLM provider via environment variables. Use npm start --prefix mcp-server-http and npm start --prefix mcp-server-sse to start the servers, then npm start --prefix mcp-host to launch the host agent. Alternatively, use docker compose up to run everything in containers.

Key features of OpenAI MCP Example

Supports Azure OpenAI, OpenAI, and GitHub Models as LLM providers.
Provides both HTTP streaming and SSE (Server-Sent Events) MCP transports.
Includes tools: add_todo, list_todos, complete_todo, delete_todo.
Persists state using DocumentDB Local database.
Debugging via DEBUG=mcp:* environment variable.

Use cases of OpenAI MCP Example

Interact with a shopping list agent that can add, list, complete, and delete items.
Test and compare different MCP transport protocols (HTTP vs SSE) with a single host.
Experiment with multiple LLM providers (OpenAI, Azure OpenAI, GitHub Models) in the same demo.

常见问题

What LLM providers are supported?

Azure OpenAI (Responses API), OpenAI (Responses API), and GitHub Models (ChatCompletion API).

What MCP transport protocols are available?

Two implementations are provided: one using HTTP streaming and one using SSE (Server-Sent Events). Both are supported by the host.

How do I run the demo with Docker?

Clone the repository, then run `docker compose up` to start the MCP servers and DocumentDB Local. Access the MCP host container with `docker exec -it mcp-host bash`.

What tools does the agent have access to?

The agent can use four tools: add_todo, list_todos, complete_todo, and delete_todo.

How can I enable debug logging?

Set the `DEBUG` environment variable to `mcp:*` before starting the MCP host, e.g., `DEBUG=mcp:* npm start --prefix mcp-host`.

AI 与智能体分类下的更多 MCP 服务器

Lumify Sports Intelligence

Lumify

Agent-ready sports intelligence API: live scores, odds, line movement, public betting splits, and explainable bet confidence — via 16 MCP tools at https://lumify.ai/mcp. Get a free key instantly — no signup, email, or ca

litshrine

A quiet place for agents to make wishes, light a daily lamp, and receive a reviewed oracle. Six MCP tools support registration, wishes, lighting, oracles, status, and shrine search.

fhirHydrant

faulkj

Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.

Gemina

Gemina Tech Ltd.

Extract, search and tag any document — invoices, receipts, contracts, forms, or your own templates. 13 tools, one sign-in (OAuth 2.1) or API key, free FileTag tier, data residency in the EU, US, Israel or Asia.

Poly-Glot AI Workspace

hmoses

1,000+ fully localized prompt templates across 40+ categories. Compare Mode — send the same prompt to up to 9 AI providers (ChatGPT, Claude, Gemini, Grok, Groq, Copilot, Mistral, Perplexity, DuckDuckGo AI) and compare an