Any Chat Completions

🚀 Any-chat-completions-mcp MCP Server

Integrate Claude into any chat completion API compatible with the OpenAI SDK, including OpenAI, Perplexity, Groq, xAI, PyroPrompts, and more.

This implementation is based on the Model Context Protocol (MCP) server. Learn more: https://modelcontextprotocol.io

This is a TypeScript-based MCP server that can be implemented into any chat completion API compatible with the OpenAI SDK.

It includes a tool chat that forwards a question to the configured AI chat provider.

🚀 Quick Start

Development

Install dependencies:

npm install

Build the server:

npm run build

Development mode with automatic rebuild:

npm run watch

📦 Installation

To add OpenAI to Claude Desktop, add the following to the configuration:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json%

{
  "mcpServers": {
    "chat-openai": {
      "command": "node",
      "args": [
        "/path/to/any-chat-completions-mcp/build/index.js"
      ],
      "env": {
        "AI_CHAT_KEY": "OPENAI_KEY",
        "AI_CHAT_NAME": "OpenAI",
        "AI_CHAT_MODEL": "gpt-4o",
        "AI_CHAT_BASE_URL": "https://api.openai.com/v1"
      }
    }
  }
}

You can extend the functionality by adding multiple providers. Each provider can reference the same MCP server but use different environment parameters:

{
  "mcpServers": {
    "chat-pyroprompts": {
      "command": "node",
      "args": [
        "/path/to/any-chat-completions-mcp/build/index.js"
      ],
      "env": {
        "AI_CHAT_KEY": "PYROPROMPTS_KEY",
        "AI_CHAT_NAME": "PyroPrompts",
        "AI_CHAT_MODEL": "ash",
        "AI_CHAT_BASE_URL": "https://api.pyroprompts.com/openaiv1"
      }
    },
    "chat-perplexity": {
      "command": "node",
      "args": [
        "/path/to/any-chat-completions-mcp/build/index.js"
      ],
      "env": {
        "AI_CHAT_KEY": "PERPLEXITY_KEY",
        "AI_CHAT_NAME": "Perplexity",
        "AI_CHAT_MODEL": "llama-3.1-sonar-small-128k-online",
        "AI_CHAT_BASE_URL": "https://api.perplexity.ai"
      }
    },
    "chat-openai": {
      "command": "node",
      "args": [
        "/path/to/any-chat-completions-mcp/build/index.js"
      ],
      "env": {
        "AI_CHAT_KEY": "OPENAI_KEY",
        "AI_CHAT_NAME": "OpenAI",
        "AI_CHAT_MODEL": "gpt-4o",
        "AI_CHAT_BASE_URL": "https://api.openai.com/v1"
      }
    }
  }
}

Debugging

Since the MCP server communicates via standard input and output, direct debugging can be a bit difficult. Therefore, it is recommended to use the Inspector tool to assist with debugging. Run the following command to access the debugging interface:

npm run inspector

Thanks

Thanks to the Model Context Protocol team and Anthropic for providing powerful technical support. Special thanks to PyroPrompts for their support and for providing a promo code: [Insert promo code here], which can be used to get free credits.