Lm

Overview

Lm is a Model Context Protocol server that connects Claude to any OpenAI-compatible LLM endpoint, letting you offload routine work to a local model. By speaking MCP, it transforms your local LLM into callable tools that Claude can use directly, eliminating the need to copy and paste between applications.

The server runs locally on your machine via the npm package @houtini/lm, which communicates over stdio. Install it with npx -y @houtini/lm. You'll need an API key for your chosen endpoint. The latest release is v3.2.3, published under the Apache-2.0 license. The source code lives at houtini-ai/lm on GitHub, where the project has earned 112 stars.

Lm belongs in the AI & Agents category on mcp.site and works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this server, claim your listing to verify ownership and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "lm": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/lm"
      ]
    }
  }
}