agentmods.dev

lm

lm is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from houtini-ai/houtini-lm. Its token cost is not measured, scanned A, original, Apache-2.0.

A local bridge that lets Claude send work to any OpenAI-compatible language-model service, including a model running on your own machine. It runs through the @houtini/lm npm package and is configured with four environment variables.

In plain words
What is it for?
Use it when connecting Claude to a compatible LLM endpoint and selecting its URL, API key, model, and provider. It is suited to delegating routine language-model work to a local model.
Why use it?
It can move routine model requests away from Claude to a configured endpoint. Running locally can keep that work within a local setup, subject to the chosen endpoint and model.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 120repo +1 6d ago A scan tokens not measured original Apache-2.0

Good fit Use it when connecting Claude to a compatible LLM endpoint and selecting its URL, API key, model, and provider. It is suited to delegating routine language-model work to a local model.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/houtini-ai/houtini-lm/lm
View source ↗ houtini-ai/houtini-lm houtini.com
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/houtini-ai/houtini-lm

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for lm

README.md
[![agentmods](https://agentmods.dev/badge/mcp/houtini-ai/houtini-lm/lm/github.svg)](https://agentmods.dev/mcp/houtini-ai/houtini-lm/lm)
Your own site
<a href="https://agentmods.dev/mcp/houtini-ai/houtini-lm/lm"><img src="https://agentmods.dev/badge/mcp/houtini-ai/houtini-lm/lm/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for lm

Your own site · 80×15
<a href="https://agentmods.dev/mcp/houtini-ai/houtini-lm/lm"><img src="https://agentmods.dev/badge/mcp/houtini-ai/houtini-lm/lm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

lm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

server.json · 15 lines

What it actually says

{
  "lm": {
    "command": "npx",
    "args": [
      "-y",
      "@houtini/lm"
    ],
    "env": {
      "HOUTINI_LM_ENDPOINT_URL": "",
      "HOUTINI_LM_API_KEY": "",
      "HOUTINI_LM_MODEL": "",
      "HOUTINI_LM_PROVIDER": ""
    }
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 15 lines scan A 0c8d1ed8eae7

Subscribe to this mod's changes

lm is an MCP server published in the GitHub repository houtini-ai/houtini-lm (120 stars, last pushed 6d ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-07.

Code GenerationData and AIai-agentsclaude-mcpdeveloper-tooldeveloper-toolslm-studio
Related

Other mcp servers, from other repositories

ask-llm

Unified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity. Runs locally from the @ask-llm/mcp npm package. Needs 16 environment variables to run.

Lykhoyda/ask-llm · not measured

ask-grok

Consult Grok through xAI's metered API with exact model selection and no fallback. Runs locally from the @ask-llm/grok-mcp npm package. Needs 7 environment variables to run.

Lykhoyda/ask-llm · not measured

short-video-maker

Creates short videos for TikTok, Instagram Reels, and YouTube Shorts using the Model Context Protocol (MCP) and a REST API. Runs locally from the short-video-maker npm package. Needs 1 environment variable to run.

vikisingh23/neuraforge-ai · not measured

sonarqube-mcp

Model Context Protocol server for SonarQube. Runs locally from the sonarqube-mcp-server npm package.

vikisingh23/neuraforge-ai · not measured

gluestack-ui-mcp

A Model Context Protocol (MCP) server for Gluestack UI components, providing AI assistants with access to component source code, demos, and metadata. Runs locally from the gluestack-ui-mcp-server npm package.

vikisingh23/neuraforge-ai · not measured

remotion-mcp

Remotion's Model Context Protocol. Runs locally from the @remotion/mcp npm package.

vikisingh23/neuraforge-ai · not measured