Any Chat Completions

any-chat-completions-mcp MCP Server

Integrate Claude with Any OpenAI SDK Compatible Chat Completion API - OpenAI, Perplexity, Groq, xAI, PyroPrompts and more.

This implements the Model Context Protocol Server. Learn more: https://modelcontextprotocol.io

This is a TypeScript-based MCP server that implements an implementation into any OpenAI SDK Compatible Chat Completions API.

It has one tool, chat which relays a question to a configured AI Chat Provider.

Claude uses OpenAI

Development

Install dependencies:

1npm install

Build the server:

1npm run build

For development with auto-rebuild:

1npm run watch

Installation

To add OpenAI to Claude Desktop, add the server config:

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

1
2{
3  "mcpServers": {
4    "chat-openai": {
5      "command": "node",
6      "args": [
7        "/path/to/any-chat-completions-mcp/build/index.js"
8      ],
9      "env": {
10        "AI_CHAT_KEY": "OPENAI_KEY",
11        "AI_CHAT_NAME": "OpenAI",
12        "AI_CHAT_MODEL": "gpt-4o",
13        "AI_CHAT_BASE_URL": "https://api.openai.com/v1"
14      }
15    }
16  }
17}

You can add multiple providers by referencing the same MCP server multiple times, but with different env arguments:

1
2{
3  "mcpServers": {
4    "chat-pyroprompts": {
5      "command": "node",
6      "args": [
7        "/path/to/any-chat-completions-mcp/build/index.js"
8      ],
9      "env": {
10        "AI_CHAT_KEY": "PYROPROMPTS_KEY",
11        "AI_CHAT_NAME": "PyroPrompts",
12        "AI_CHAT_MODEL": "ash",
13        "AI_CHAT_BASE_URL": "https://api.pyroprompts.com/openaiv1"
14      }
15    },
16    "chat-perplexity": {
17      "command": "node",
18      "args": [
19        "/path/to/any-chat-completions-mcp/build/index.js"
20      ],
21      "env": {
22        "AI_CHAT_KEY": "PERPLEXITY_KEY",
23        "AI_CHAT_NAME": "Perplexity",
24        "AI_CHAT_MODEL": "llama-3.1-sonar-small-128k-online",
25        "AI_CHAT_BASE_URL": "https://api.perplexity.ai"
26      }
27    },
28    "chat-openai": {
29      "command": "node",
30      "args": [
31        "/path/to/any-chat-completions-mcp/build/index.js"
32      ],
33      "env": {
34        "AI_CHAT_KEY": "OPENAI_KEY",
35        "AI_CHAT_NAME": "OpenAI",
36        "AI_CHAT_MODEL": "gpt-4o",
37        "AI_CHAT_BASE_URL": "https://api.openai.com/v1"
38      }
39    }
40  }
41}

With these three, you'll see a tool for each in the Claude Desktop Home:

Claude Desktop Home with Chat Tools

And then you can chat with other LLMs and it shows in chat like this:

Claude Chat with OpenAI

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

1npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

Acknowledgements

Obviously the modelcontextprotocol and Anthropic team for the MCP Specification and integration into Claude Desktop. https://modelcontextprotocol.io/introduction
PyroPrompts for sponsoring this project. Use code CLAUDEANYCHAT for 20 free automation credits on Pyroprompts.

Contents