OpenAI is a AI & ML MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent gPT models, DALL-E, Whisper via OpenAI API. Install in 1 minute with mcpizy install openai.
Connect your OpenAI account once — MCPizy stores the credentials encrypted and uses them whenever you run a recipe in managed mode.
mcpizy install openainpx -y openai-mcp-serverchat_completionCall an OpenAI chat model
Inputs
modelstringrequiredmessagesobject[]requiredcreate_imageGenerate images with DALL-E
Inputs
promptstringrequiredsizestringoptionalcreate_embeddingCreate a text embedding
Inputs
inputstringrequiredmodelstringoptionallist_modelsList available OpenAI models
transcribe_audioTranscribe audio with Whisper
Inputs
filestringrequiredWorks identically across clients. Only the config file path differs.
~/.claude.json{
"mcpServers": {
"openai": {
"command": "npx",
"args": [
"-y",
"openai-mcp-server"
],
"env": {
"OPENAI_API_KEY": "sk-..."
}
}
}
}.cursor/mcp.json{
"mcpServers": {
"openai": {
"command": "npx",
"args": [
"-y",
"openai-mcp-server"
],
"env": {
"OPENAI_API_KEY": "sk-..."
}
}
}
}~/.codeium/windsurf/mcp_config.json{
"mcpServers": {
"openai": {
"command": "npx",
"args": [
"-y",
"openai-mcp-server"
],
"env": {
"OPENAI_API_KEY": "sk-..."
}
}
}
}Create an API key in the OpenAI platform
OPENAI_API_KEYPaste any of these prompts into Claude Code, Cursor or another MCP-compatible client.
“Ask GPT-4o to summarise this 10-page PDF”
Uses: chat_completion
“Generate a 1024x1024 image of a cyberpunk cat”
Uses: create_image
“Embed these 3 product descriptions for semantic search”
Uses: create_embedding
“Transcribe the meeting.mp3 file”
Uses: transcribe_audio
AI-powered codebase context. Understand any GitHub repo instantly with semantic code search.
Open-source LLM observability. Collaborative prompt editing, tracing, and evaluation.
Predict anything with AI forecasting. Time series predictions, anomaly detection, and trend analysis.
Models, datasets, and spaces on HF
If OpenAI doesn't fit your stack, these AI & ML MCP servers solve similar problems.
The OpenAI MCP server is an AI & ML Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents gPT models, DALL-E, Whisper via OpenAI API. It exposes OpenAI's capabilities as tools the AI can call directly from your editor or CLI.
The fastest way is the MCPizy CLI: run `mcpizy install openai` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `npx -y openai-mcp-server` and restarting Claude Code.
Yes. The OpenAI MCP server is free and open source (see the GitHub repository linked on this page). You may still need a OpenAI account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.
Yes. Any MCP-compatible client works — including Claude Code, Claude Desktop, Cursor (via `.cursor/mcp.json`), Windsurf, VS Code with Copilot Chat, and custom agents built on the MCP SDK. The same install command targets all of them; only the config file path differs.
Once installed, your AI agent can gPT models, DALL-E, Whisper via OpenAI API directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run OpenAI operations, inspect results, chain OpenAI with other MCP servers (see our Workflow Recipes), and automate repetitive ai & ml tasks without leaving your editor.