Any Chat Completions

What is any-chat-completions-mcp?

any-chat-completions-mcp is a Model Context Protocol (MCP) server that enables integration with various OpenAI SDK Compatible Chat Completions APIs, such as OpenAI, Perplexity, Groq, and xAI. It acts as a bridge, allowing applications like Claude Desktop and LibreChat to utilize different large language models (LLMs) through a unified interface.

How to use any-chat-completions-mcp?

To use any-chat-completions-mcp, you can either install it via npx or clone the repository and build it locally. The server is configured by modifying the claude_desktop_config.json file (for Claude Desktop) or similar configuration for other applications like LibreChat. You define mcpServers entries, specifying the command to run the server (either npx or node with the build path) and environment variables for AI_CHAT_KEY, AI_CHAT_NAME, AI_CHAT_MODEL, and AI_CHAT_BASE_URL to connect to different LLM providers. Multiple providers can be configured by adding separate entries.

Key Features of any-chat-completions-mcp

• OpenAI SDK Compatibility: Seamlessly integrates with any LLM that is compatible with the OpenAI SDK.
• Unified Tool: Provides a single chat tool to relay questions to configured AI chat providers.
• Multi-Provider Support: Allows configuration and use of multiple LLM providers simultaneously (e.g., OpenAI, Perplexity, PyroPrompts).
• Easy Integration: Designed for straightforward integration with MCP-compatible applications like Claude Desktop and LibreChat.
• Development Tools: Includes scripts for building, watching for changes, and debugging with the MCP Inspector.
• Smithery Integration: Can be installed automatically via Smithery CLI.

Use Cases of any-chat-completions-mcp

• Expanding LLM Access in Claude Desktop: Enables Claude Desktop users to interact with a wider range of LLMs beyond its native capabilities.
• Flexible LLM Integration in LibreChat: Allows LibreChat users to easily switch between and utilize different chat completion APIs.
• Developing LLM-Powered Applications: Provides a standardized way for developers to incorporate various LLMs into their applications using the MCP.
• Experimenting with Different LLMs: Facilitates testing and comparing the performance of different LLMs for specific tasks.

FAQ from any-chat-completions-mcp

Q: How do I debug the MCP server? A: Since MCP servers communicate over stdio, debugging can be challenging. It is recommended to use the MCP Inspector, which can be accessed by running npm run inspector.

Q: Can I use multiple LLM providers with this server? A: Yes, you can configure multiple LLM providers by adding separate entries in your mcpServers configuration, each with different environment variables for the desired provider.

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.