How do I use llmsproxy?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@llmsproxy explain the transformer architecture" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

@llmsproxy/mcp-server

The Model Context Protocol server for llmsproxy.ai. It connects Claude Desktop, Cursor, Cline, Zed, and any other MCP client to your llmsproxy.ai account, exposing chat, coding, and retrieval capabilities as MCP tools, resources, and prompts.

You bring an llms_live_… API key from your llmsproxy.ai dashboard; this server speaks JSON-RPC 2.0 over stdio and forwards your requests to the gateway.

Install

The quickest path is the hosted installer, which configures Claude Desktop for you:

curl -fsSL https://llmsproxy.ai/mcp/install.sh | bash

Or wire it into any MCP client manually:

{
  "mcpServers": {
    "llmsproxy": {
      "command": "npx",
      "args": ["-y", "@llmsproxy/mcp-server"],
      "env": {
        "LLMSPROXY_API_KEY": "llms_live_...",
        "LLMSPROXY_BASE_URL": "https://api.llmsproxy.ai/v1"
      }
    }
  }
}

Related MCP server: 1mcpserver

Configuration

Environment variable	Required	Description
`LLMSPROXY_API_KEY`	yes	Your `llms_live_…` API key from the llmsproxy.ai dashboard.
`LLMSPROXY_BASE_URL`	no	Gateway API root. Defaults to `https://api.llmsproxy.ai/v1`.

Supported platforms

darwin-arm64, darwin-x64, linux-arm64, linux-x64, win32-x64.

The package ships a small Node shim that selects and runs the prebuilt binary for your platform — installed automatically as an optional dependency. No build step, no network access at install time, no postinstall scripts.