PluginBench
MCP Server
Active
Apache-2.0

io.github.houtini-ai/lm MCP Server

io.github.houtini-ai/lm

What is the io.github.houtini-ai/lm MCP server?

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

How to install io.github.houtini-ai/lm

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • 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.

Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "lm": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/lm"
      ],
      "env": {
        "HOUTINI_LM_ENDPOINT_URL": "<YOUR_HOUTINI_LM_ENDPOINT_URL>",
        "HOUTINI_LM_API_KEY": "<YOUR_HOUTINI_LM_API_KEY>",
        "HOUTINI_LM_MODEL": "<YOUR_HOUTINI_LM_MODEL>",
        "HOUTINI_LM_PROVIDER": "<YOUR_HOUTINI_LM_PROVIDER>"
      }
    }
  }
}
Cursor
~/.cursor/mcp.json
{
  "mcpServers": {
    "lm": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/lm"
      ],
      "env": {
        "HOUTINI_LM_ENDPOINT_URL": "<YOUR_HOUTINI_LM_ENDPOINT_URL>",
        "HOUTINI_LM_API_KEY": "<YOUR_HOUTINI_LM_API_KEY>",
        "HOUTINI_LM_MODEL": "<YOUR_HOUTINI_LM_MODEL>",
        "HOUTINI_LM_PROVIDER": "<YOUR_HOUTINI_LM_PROVIDER>"
      }
    }
  }
}
Windsurf
~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "lm": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/lm"
      ],
      "env": {
        "HOUTINI_LM_ENDPOINT_URL": "<YOUR_HOUTINI_LM_ENDPOINT_URL>",
        "HOUTINI_LM_API_KEY": "<YOUR_HOUTINI_LM_API_KEY>",
        "HOUTINI_LM_MODEL": "<YOUR_HOUTINI_LM_MODEL>",
        "HOUTINI_LM_PROVIDER": "<YOUR_HOUTINI_LM_PROVIDER>"
      }
    }
  }
}
VS Code
.vscode/mcp.json
{
  "servers": {
    "lm": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@houtini/lm"
      ],
      "env": {
        "HOUTINI_LM_ENDPOINT_URL": "<YOUR_HOUTINI_LM_ENDPOINT_URL>",
        "HOUTINI_LM_API_KEY": "<YOUR_HOUTINI_LM_API_KEY>",
        "HOUTINI_LM_MODEL": "<YOUR_HOUTINI_LM_MODEL>",
        "HOUTINI_LM_PROVIDER": "<YOUR_HOUTINI_LM_PROVIDER>"
      }
    }
  }
}
Claude Code
claude mcp add lm --env HOUTINI_LM_ENDPOINT_URL=<YOUR_HOUTINI_LM_ENDPOINT_URL> --env HOUTINI_LM_API_KEY=<YOUR_HOUTINI_LM_API_KEY> --env HOUTINI_LM_MODEL=<YOUR_HOUTINI_LM_MODEL> --env HOUTINI_LM_PROVIDER=<YOUR_HOUTINI_LM_PROVIDER> -- npx -y @houtini/lm

Related MCP servers

Model Context Protocol server for Google Gemini AI with chat, research, and grounding

30
TypeScript
Apache-2.0
View repository →

Scores content on the signals that get it cited by ChatGPT, Perplexity and AI Overviews

21
TypeScript
MIT
View repository →

Crawl and analyse websites for SEO errors using Crawlee with SQLite storage

16
TypeScript
Apache-2.0
View repository →

Multi-URL comparative content analysis with topical gap detection

12
TypeScript
Apache-2.0
View repository →

Search Google's Knowledge Graph for structured information about real-world entities

10
TypeScript
MIT
View repository →

Technical SEO in Claude: GSC + crawl + DataForSEO - audit, market sizing, content recon.

5
TypeScript
Apache-2.0
View repository →