Any Chat Completions MCP

What is Any Chat Completions MCP about?

Enables Claude Desktop, LibreChat and any MCP‑compatible client to treat an arbitrary OpenAI‑style chat completion API as a native tool, allowing users to query models such as OpenAI, Perplexity, Groq, xAI, PyroPrompts, etc.

How to use Any Chat Completions MCP?

1. Installation – install the package via npx or clone the repository and build it.
2. Configure – add an MCP server entry to the client’s configuration (Claude Desktop, LibreChat, etc.) pointing to the package and supplying the required environment variables (AI_CHAT_KEY, AI_CHAT_NAME, AI_CHAT_MODEL, AI_CHAT_BASE_URL).
3. Run – the server runs as a stdio process; the client communicates with it using the Model Context Protocol.
4. Interact – select the generated “chat” tool in the client UI and ask questions; the server forwards them to the chosen provider and returns the response.

Key Features

• Single chat tool that proxies any OpenAI‑compatible chat completion endpoint.
• Works with multiple providers simultaneously by defining several server entries with different env values.
• Supports both npx‑based quick run and compiled Node.js binary for production use.
• Debugging support via the MCP Inspector.
• Ready‑made installation via Smithery for Claude Desktop.

Use Cases

• Multi‑model switching – effortlessly switch between OpenAI, Perplexity, Groq, etc., within the same client.
• Custom provider integration – expose a private or niche LLM that offers an OpenAI‑style API.
• Rapid prototyping – test new models without modifying the client code.
• Enterprise setups – run the server behind internal firewalls and connect internal LLMs to Claude Desktop.

FAQ

Q: Do I need to modify Claude Desktop code? A: No. Adding the MCP server entry to claude_desktop_config.json is sufficient.

Q: Can I run multiple instances for different models? A: Yes. Define separate entries with distinct environment variables.

Q: What if my provider requires additional headers? A: Set them via the standard AI_CHAT_* environment variables or extend the server code.

Q: How do I debug communication problems? A: Use npm run inspector to launch the MCP Inspector, which provides a web UI for tracing stdio messages.

Q: Is TypeScript required to run the server? A: No. After building, you can run the compiled JavaScript with Node.js or invoke the package directly via npx.

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.

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm 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

You can use it via npx in your Claude Desktop configuration like this:

{
  "mcpServers": {
    "chat-openai": {
      "command": "npx",
      "args": [
        "@pyroprompts/any-chat-completions-mcp"
      ],
      "env": {
        "AI_CHAT_KEY": "OPENAI_KEY",
        "AI_CHAT_NAME": "OpenAI",
        "AI_CHAT_MODEL": "gpt-4o",
        "AI_CHAT_BASE_URL": "https://api.openai.com/v1"
      }
    }
  }
}

Or, if you clone the repo, you can build and use in your Claude Desktop configuration like this:

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

{
  "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": "sonar",
        "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"
      }
    }
  }
}

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

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

Or, configure in LibreChat like:

  chat-perplexity:
    type: stdio
    command: npx
    args:
      - -y
      - @pyroprompts/any-chat-completions-mcp
    env:
      AI_CHAT_KEY: "pplx-012345679"
      AI_CHAT_NAME: Perplexity
      AI_CHAT_MODEL: sonar
      AI_CHAT_BASE_URL: "https://api.perplexity.ai"
      PATH: '/usr/local/bin:/usr/bin:/bin'

And it shows in LibreChat:

Installing via Smithery

To install Any OpenAI Compatible API Integrations for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install any-chat-completions-mcp-server --client claude

Debugging

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

npm 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.