Sends messages to OpenAI's chat completion API. Supports models like gpt-4o, gpt-4o-mini, o1-preview, and o1-mini.
This integration allows you to seamlessly use OpenAI's powerful language models directly within Claude Desktop. With support for multiple models including GPT-4o, GPT-4o-mini, o1-preview, and o1-mini, you can leverage OpenAI's capabilities without leaving your Claude environment. The integration provides a simple message passing interface that makes it easy to switch between Claude and OpenAI models during your conversations.
The OpenAI Integration allows you to access OpenAI's language models directly from within Claude Desktop. This enables you to leverage the unique strengths of different AI models in a single interface, creating a more versatile and powerful AI assistant experience.
Before installing this integration, you'll need:
To install the OpenAI Integration:
Make sure you have the Claude Desktop application installed
Obtain an OpenAI API key from the OpenAI platform
Locate your Claude Desktop configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
Add the following configuration to your claude_desktop_config.json
file:
{
"mcpServers": {
"mcp-openai": {
"command": "npx",
"args": ["-y", "@mzxrai/mcp-openai@latest"],
"env": {
"OPENAI_API_KEY": "your-api-key-here"
}
}
}
}
"your-api-key-here"
with your actual OpenAI API keyOnce installed, you can use OpenAI models by simply asking Claude to use them in your conversation. For example:
The integration currently supports the following OpenAI models:
If you encounter any issues:
tail -n 20 -f ~/Library/Logs/Claude/mcp*.log