Description

A unified gateway server for managing interactions with multiple LLM providers (OpenAI, Anthropic, DeepSeek, Gemini) with built-in cost optimization, caching, and monitoring. Features include automatic model selection based on task requirements, semantic caching to reduce redundant API calls, detailed usage analytics, and a CLI for direct interaction. The implementation focuses on reliability with comprehensive error handling, request retries, and rate limiting, making it particularly valuable for production deployments that need to balance performance and costs across multiple LLM providers.

Installation

git clone https://github.com/dicklesworthstone/ultimate_mcp_server

Claude Desktop Configuration

Add this configuration to your Claude Desktop config file to enable this MCP server:

Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json

Config file location: %APPDATA%\Claude\claude_desktop_config.json

Config file location: ~/.config/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "llm-gateway": {
      "command": "node",
      "args": [
        "path/to/server.js"
      ]
    }
  }
}