Lm

MCP server · by houtini-ai

AI & ML npm v3.3.4

Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.

View source ↗ Website ↗ Generate config for multiple servers More servers

Install

Pin version registry version 3.3.4

npm
npx -y @houtini/lm

npm
npx -y @houtini/lm@3.3.4

Setup by client

Pick your client — the config below is generated for this server (local stdio). Copy respects the “Pin version” switch above.

claude_desktop_config.json

{
  "mcpServers": {
    "lm": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/lm"
      ],
      "env": {
        "HOUTINI_LM_API_KEY": "<YOUR_HOUTINI_LM_API_KEY>"
      }
    }
  }
}

{
  "mcpServers": {
    "lm": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/lm@3.3.4"
      ],
      "env": {
        "HOUTINI_LM_API_KEY": "<YOUR_HOUTINI_LM_API_KEY>"
      }
    }
  }
}

Format verified against the official Claude Desktop docs ↗.

terminal

claude mcp add --env HOUTINI_LM_API_KEY=<YOUR_HOUTINI_LM_API_KEY> lm -- npx -y @houtini/lm

claude mcp add --env HOUTINI_LM_API_KEY=<YOUR_HOUTINI_LM_API_KEY> lm -- npx -y @houtini/lm@3.3.4

Format verified against the official Claude Code docs ↗.

.cursor/mcp.json

{
  "mcpServers": {
    "lm": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/lm"
      ],
      "env": {
        "HOUTINI_LM_API_KEY": "<YOUR_HOUTINI_LM_API_KEY>"
      }
    }
  }
}

{
  "mcpServers": {
    "lm": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/lm@3.3.4"
      ],
      "env": {
        "HOUTINI_LM_API_KEY": "<YOUR_HOUTINI_LM_API_KEY>"
      }
    }
  }
}

Format verified against the official Cursor docs ↗.

.vscode/mcp.json

{
  "servers": {
    "lm": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/lm"
      ],
      "env": {
        "HOUTINI_LM_API_KEY": "<YOUR_HOUTINI_LM_API_KEY>"
      }
    }
  }
}

{
  "servers": {
    "lm": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/lm@3.3.4"
      ],
      "env": {
        "HOUTINI_LM_API_KEY": "<YOUR_HOUTINI_LM_API_KEY>"
      }
    }
  }
}

Format verified against the official VS Code docs ↗.

mcp_config.json

{
  "mcpServers": {
    "lm": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/lm"
      ],
      "env": {
        "HOUTINI_LM_API_KEY": "<YOUR_HOUTINI_LM_API_KEY>"
      }
    }
  }
}

{
  "mcpServers": {
    "lm": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/lm@3.3.4"
      ],
      "env": {
        "HOUTINI_LM_API_KEY": "<YOUR_HOUTINI_LM_API_KEY>"
      }
    }
  }
}

Format verified against the official Windsurf docs ↗.

Environment variables

Defined in the server's official registry manifest. Required secrets are shown as <YOUR_…> placeholders in the configs above.

HOUTINI_LM_ENDPOINT_URL — Base URL of the OpenAI-compatible API endpoint (e.g. http://localhost:1234, https://openrouter.ai/api). Legacy alias: LM_STUDIO_URL.
HOUTINI_LM_API_KEY secret — Bearer token for API authentication (no auth if blank). Legacy aliases: LM_STUDIO_PASSWORD, LM_PASSWORD, OPENROUTER_API_KEY.
HOUTINI_LM_MODEL — Model identifier to use for requests (auto-detected if not set). Legacy alias: LM_STUDIO_MODEL.
HOUTINI_LM_PROVIDER — Optional provider override: 'openrouter' forces OpenRouter-specific handling (attribution headers, reasoning.exclude, no inference serialisation). Auto-detected from the endpoint URL when possible.

GitHub

⭐ 121 stars · 最近更新于 33 天前 · Apache-2.0 license

About this server

/ Houtini LM (@houtini/lm) Offload Work from Claude Code to a Local LLM, OpenAI GPT 5/6, a Router or a Cheaper Cloud Model Houtini LM is an MCP…

Summary from the project README — github.com/houtini-ai/houtini-lm

Distributed as npm, listed under AI & ML. Review our MCP security guide before granting access to real data.

Frequently asked questions

What does the Lm MCP server do?

/ Houtini LM (@houtini/lm) Offload Work from Claude Code to a Local LLM, OpenAI GPT 5/6, a Router or a Cheaper Cloud Model Houtini LM is an MCP

How do I install Lm?

Run the install command shown above, then paste the config for your client (Claude Desktop, Claude Code, Cursor, VS Code or Windsurf) into its MCP settings and restart the client.

Is Lm free to use?

The MCP server itself is free to install. The source is public on https://github.com/houtini-ai/houtini-lm. Any third-party service it calls may require its own API key and account.

Which clients support Lm?

Any MCP-compatible client can use it, including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and custom agents.

Add this badge

Publish this server? Link back with a badge on your README or site — copy either snippet.

Markdown

[![Listed on MCPNav](https://mcpnav.net/badge/lm.svg)](https://mcpnav.net/server/lm/)

HTML

<a href="https://mcpnav.net/server/lm/"><img src="https://mcpnav.net/badge/lm.svg" alt="Listed on MCPNav" height="20"></a>