Lm MCP Server

Houtini LM is an MCP server that lets Claude (or any MCP client) hand bounded work to another model - a local LLM on your GPU, OpenAI's latest GPT models, a LiteLLM router, OpenRouter or a cheap cloud API - while you carry on working in the AI platform you already like. It cuts your token bill, and it gives you a second model to review your code whenever you want one.

People who work with claude mcp, code generation and developer tool and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.

VERIFIED ACTIVE

LAST COMMIT 2026-09-24 · ★ 120 · #17 OF 250 MAINTAINED CODING AGENT · VERIFIED 2026-09-30

Apache-2.0 · TypeScript servers · how we verify → /methodology

01 · Install Lm

before you install - you'll need

Set HOUTINI_LM_ENDPOINT_URL, HOUTINI_LM_API_KEY, HOUTINI_LM_MODEL, HOUTINI_LM_SERIALISE before connecting.

Claude Code

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

Claude Desktop / Cursor / VS Code - add to config

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

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license Apache-2.0 - declared in the repository

npm package @houtini/lm - the @houtini scope differs from the repo owner (houtini-ai); confirm it's the project's official package

registry namespace io.github.houtini-ai is GitHub-verified and matches the repo owner

03 · What Lm can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v2.8.0 · 2026-03-18

What's New · Added · Quality metadata - every response includes structured quality signals (truncation, think-block detection, token estimation, finish reason) so Claude can make informed trust decisions about local…

v1.0.13 · 2025-09-23

Local LLM MCP v1.0.13 · 1.0.13

v1.0.12 · 2025-09-23

Local LLM MCP v1.0.12 · 1.0.12

04 · Who maintains Lm

lm is maintained by houtini-ai. We track 9 MCP servers from houtini-ai - 7 actively maintained, 251 combined GitHub stars, oldest repo from Sep 2025. Full record: all servers from houtini-ai.

  1. seo-audit-console Technical SEO in Claude: GSC + crawl + DataForSEO - audit, market sizing, content recon. ★ 34
  2. geo-analyzer Scores content on the signals that get it cited by ChatGPT, Perplexity and AI Overviews ★ 21
  3. amazon-creators Amazon product search returning paste-ready affiliate deal rows for your blog ★ 2
  4. google-knowledge-graph Search Google's Knowledge Graph for structured information about real-world entities ★ 11
  5. fanout Multi-URL comparative content analysis with topical gap detection ★ 12
  6. seo-crawler-mcp Crawl and analyse websites for SEO errors using Crawlee with SQLite storage ★ 16

05 · Facts

category
coding agent - ranked #17 of 250 actively-maintained coding agent servers as of 2026-09-30.
registry
io.github.houtini-ai/lm (active, first published 2026-08-04 · 4 versions)
packages
npm:@houtini/lm

06 · Lm FAQ

What is Lm?

Houtini LM is an MCP server that lets Claude (or any MCP client) hand bounded work to another model - a local LLM on your GPU, OpenAI's latest GPT models, a LiteLLM router, OpenRouter or a cheap cloud API - while you carry on working in the AI platform you already like. It cuts your token bill, and it gives you a second model to review your code whenever you want one.

Is Lm still maintained?

Yes - as of 2026-09-30, its last commit was 2026-09-24. We re-verify nightly.

How do I install Lm?

Run `npx -y @houtini/lm`. The README documents 4 environment variables (HOUTINI_LM_ENDPOINT_URL, HOUTINI_LM_API_KEY, HOUTINI_LM_MODEL…) to set first. Set HOUTINI_LM_ENDPOINT_URL, HOUTINI_LM_API_KEY, HOUTINI_LM_MODEL, HOUTINI_LM_SERIALISE before connecting. You can also paste the ready-made client config above.

Does Lm run locally?

Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Lm