Lm MCP Server

by houtini-ai Your server? Claim it

local only

Lm runs on your own machine — the client starts it, so there is no endpoint to ping. 284 installs a week from npm. Last commit 15 Aug 2026.

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

Installs per day peak 251 · avg 58 · -31% w/w

a month agotoday

284

Installs / week

npm · @houtini/lm

113

Stars

9 open issues

15 Aug 2026

Last commit

0 releases in 90 days

Apache-2.0

License

JavaScript

Nothing serious here today

Today is the operative word: we check Lm every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add lm -- npx -y @houtini/lm

~/Library/Application Support/Claude/claude_desktop_config.json

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

~/.codex/config.toml

[mcp_servers.lm]
command = "npx"
args = ["-y", "@houtini/lm"]

.cursor/mcp.json

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

.vscode/mcp.json

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

Alternatives to Lm

same job, measured the same way

Local Delegate

by zahirinatzuke

Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota.

633 installs/wk local only

Qsp MCP

by qso-graph

QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)

68 installs/wk local only

Claude Token Saver MCP

by blackfoil

MCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens

77 installs/wk local only

Ollama Handoff

by michael-whitecapdata

Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.

107 installs/wk local only

LooperTask

by loopertask

AI-native Kanban board — connect Claude to claim, work and move your tasks over MCP.

answering

Routara LLM Gateway

by 36412749-collab

OpenAI-compatible LLM, image and video APIs via Routara (api.routara.ai).

73 installs/wk local only

freellmpool

by 0xzr

OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.

1 546 installs/wk local only

toolweave

by andreysparish

One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.

answering

Lm — questions

Answers built from our own checks of this server.

Why is there no uptime for Lm?

Lm runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @houtini/lm was installed 284 times last week.

How do I connect Lm?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls @houtini/lm straight from npm; nothing to host, nothing to sign up for.

How many people use Lm?

The npm package @houtini/lm was installed 284 times in the last week. Week over week that is -31%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Lm open source?

Yes — it is published under the Apache-2.0 licence, written in JavaScript, 113 stars on GitHub and 9 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.