houtini-lm MCP Server

Install or run

npx -y @houtini/lm

Client configuration

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "Houtini LM",
  "description": "MCP server that connects Claude to any OpenAI-compatible LLM endpoint. Offload routine analysis to a local model and preserve your Claude context window.",
  "icon": "https://houtini.ai/favicon.ico",
  "repository": {
    "url": "https://github.com/houtini-ai/lm",
    "source": "github"
  },
  "version": "3.2.2",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "@houtini/lm",
      "version": "3.2.2",
      "transport": [
        {
          "type": "stdio"
        }
      ],
      "environmentVariables": [
        {
          "name": "HOUTINI_LM_ENDPOINT_URL",
          "description": "Base URL of the OpenAI-compatible API endpoint (e.g. http://localhost:1234, https://openrouter.ai/api). Legacy alias: LM_STUDIO_URL.",
          "isRequired": false,
          "format": "url"
        },
        {
          "name": "HOUTINI_LM_API_KEY",
          "description": "Bearer token for API authentication (no auth if blank). Legacy aliases: LM_STUDIO_PASSWORD, LM_PASSWORD, OPENROUTER_API_KEY.",
          "isRequired": false,
          "isSecret": true,
          "format": "string"
        },
        {
          "name": "HOUTINI_LM_MODEL",
          "description": "Model identifier to use for requests (auto-detected if not set). Legacy alias: LM_STUDIO_MODEL.",
          "isRequired": false,
          "format": "string"
        },
        {
          "name": "HOUTINI_LM_PROVIDER",
          "description": "Optional provider override: 'openrouter' forces OpenRouter-specific handling (attribution headers, reasoning.exclude, no inference serialisation). Auto-detected from the endpoint URL when possible.",
          "isRequired"

Compatible clients