MCP.so
ログイン

OpenAI MCP Server

@MCP-Mirror

リポジトリ

OpenAI MCP Server について

Mirror of

#openai#mcp-server#api-integration

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

公開者

MCP-Mirror

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "openai-server": {
      "command": "python",
      "args": [
        "-m",
        "src.mcp_server_openai.server"
      ],
      "env": {
        "PYTHONPATH": "C:/path/to/your/mcp-server-openai",
        "OPENAI_API_KEY": "your-key-here"
      }
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is OpenAI MCP Server?

OpenAI MCP Server is an MCP (Model Context Protocol) server that lets you query OpenAI models directly from Claude. It bridges OpenAI’s API with Claude’s interface, enabling seamless AI model switching within Claude Desktop.

How to use OpenAI MCP Server?

Install the server from GitHub, then add it to your claude_desktop_config.json with the command python -m src.mcp_server_openai.server. Set the OPENAI_API_KEY environment variable to your key and point PYTHONPATH to the server’s directory.

Key features of OpenAI MCP Server

  • Queries OpenAI models directly from Claude
  • Integrates via the Model Context Protocol
  • Easy configuration in claude_desktop_config.json
  • Simple Python-based setup and execution

Use cases of OpenAI MCP Server

  • Using OpenAI’s GPT models as a fallback or alternative inside Claude
  • Comparing OpenAI and Claude outputs without switching apps
  • Automating tasks that require specific OpenAI model capabilities

FAQ from OpenAI MCP Server

What does OpenAI MCP Server do exactly?

It acts as an MCP server that Claude can call to send prompts to OpenAI’s API and return the model’s responses back to Claude.

What are the dependencies and runtime requirements?

You need Python, an OpenAI API key, and Claude Desktop (or any MCP client). The server runs as a local process using stdio transport.

How do I authenticate with OpenAI?

Set your OpenAI API key in the OPENAI_API_KEY environment variable inside the server’s configuration.

Where does my data live?

All data stays on your machine; the server sends prompts and receives responses directly via the OpenAI API. No data is stored locally by the server itself.

Are there any known limits or restrictions?

The README does not document specific limits. The server relies on your OpenAI API key’s rate limits and quotas.

コメント

「AI とエージェント」の他のコンテンツ

MCP Server - Remote MacOs Use

baryhuang

The only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App

487

MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages

utensils

MCP-NixOS - Model Context Protocol Server for NixOS resources

739

Gemini MCP Server

aliargun

MCP server implementation for Google's Gemini API

259

Solon Ai

opensolon

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

416

Sequential Thinking Multi-Agent System (MAS)

FradSer

An advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.

306