pyroprompts/any-chat-completions-mcp

Overview

A Model Context Protocol server that wraps any OpenAI-compatible chat completions API as a tool. It exposes LLM calls as MCP tools, enabling integration with MCP-compatible clients like Claude Desktop or custom workflows.

Best for

Best for
Developers building MCP-based agent workflows who need flexible LLM tool access

Use cases

• Call any LLM from within MCP-compatible environments
• Swap between different LLM providers without code changes
• Build workflows that chain LLM calls with other MCP tools

How to use

Install

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

Tools exposed

• chat

Tested with

Claude Desktop, ChatGPT, LibreChat

Example client config

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

Notes

A Model Context Protocol server that wraps any OpenAI-compatible chat completions API as a tool. It exposes LLM calls as MCP tools, enabling integration with MCP-compatible clients like Claude Desktop or custom workflows.

151 stars on GitHub. Last updated 2025-05-01. Licensed MIT.

Use cases

• Call any LLM from within MCP-compatible environments
• Swap between different LLM providers without code changes
• Build workflows that chain LLM calls with other MCP tools

Pros

• Works with any OpenAI-compatible API, including local models
• Simple setup as a single MCP server
• Lightweight JavaScript implementation

Cons

• Requires MCP-compatible client or host to be useful
• Limited to chat completions endpoints, not other API features
• Relies on OpenAI API format, potential compatibility issues with non-standard APIs

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.