MCP.Market

Lm MCP server

by houtini-ai·io.github.houtini-ai/lm·v3.3.4·121 stars
No reviews yet

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

A85/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A85/100

full report

Adoption
Established

121 stars412 downloads/wk

Reviews

Write one

Nobody has reviewed Lm yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Lm tools (8, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • chatwrite action

    Send a task to a local LLM - a sidekick running on the user's hardware or a configured OpenAI-compatible endpoint.

  • code_taskwrite action

    Send a code-specific task to the local LLM, wrapped with an optimised code-review system prompt. Temperature is locked low (0.2 or the routed model's hint) for deterministic output.

  • code_task_files

    Like code_task, but the local LLM reads files directly from disk - source never passes through the MCP client's context window. Use when reviewing multiple files or a single large file.

  • custom_prompt

    Structured analysis via the local LLM with explicit system/context/instruction separation.

  • discover

    Check whether the local LLM is online and what model is loaded. Returns model name, context window size,

  • embed

    Generate text embeddings via the local LLM server. Requires an embedding model to be loaded

  • list_models

    List all models on the local LLM server - both loaded (ready) and available (downloaded but not active).

  • stats

    Show user stats: tokens offloaded, calls made, per-model performance - for the current session AND

Public scan report

scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it

no findings
  • Code scan18 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 10 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
Overall 85/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Lm compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
85/100
higher than 75% of 4,456 AI and agents servers
Tools
8
the typical AI and agents server has 7
Tools that change things
25%
typical: 3%. Fewer write tools means less an agent can break
GitHub stars
121
more than 95% of 2,733 AI and agents servers
Downloads a week
412
more than 85% of 1,712 AI and agents servers with a package

What its tools let an agent do: 6 read · 2 change

Release history: 4 versions in the registry since 2026-08-04, latest 2026-10-07, typically one every 13 days.

Install Lm in Claude Code, Cursor or VS Code

Runs npx -y @houtini/lm on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add lm -- npx -y @houtini/lm
Add to Cursor

What the publisher says

From the Lm repository's README, as published. We do not edit it. Read it on GitHub

Houtini LM (@houtini/lm) - Offload Work from Claude Code to a Local LLM, a Router or a Cheaper Cloud Model

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, 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.

Quick Navigation

Why use it | Install | How it handles different models | What to hand over | Tools | Reading the footer | Configuration | Endpoints | The manual

I built this because I kept leaving Claude Code running overnight on big refactors and the token bill was painful. A huge chunk of that spend went on bounded tasks any decent model handles fine - generating boilerplate, code review, commit messages, format conversion, the sort of work that doesn't need Claude's reasoning or its tool access.

So Claude stays the architect, doing the planning, the multi-file changes and the judgement calls, and houtini-lm passes the drafting to whatever model you've got running. That could be Qwen on a GPU box under your desk, a model behind a LiteLLM router, one of OpenRouter's 300+ models or DeepSeek at pennies per million tokens. Claude QAs everything that comes back.

I wrote a full walkthrough of why I built this and how I use it day to day if you'd like the longer story.

Why use houtini-lm?

The bottom line before we go deep: you keep your favourite AI platform, and you stop paying frontier prices for work that doesn't need a frontier model.

The obvious win is cost. When Claude delegates a review with codetaskfiles, the source files are read by the houtini-lm process and sent straight to the other model, so they never enter Claude's context window at all. Claude sends a short tool call and reads back a short answer. I benchmarked this on real TypeScript source files:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Lm: common questions

Is Lm MCP server safe?
Yes, by our scan: it is graded A (85/100). Read the Lm safety report
How do I install Lm?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Lm need an API key?
Yes. The registry entry asks for HOUTINI_LM_API_KEY.
Is Lm maintained?
The last commit was 21 days ago (2026-10-25). The latest release is v3.3.4.
What can I use instead of Lm?
Servers from other publishers that do the same job: freellmpool MCP server, Memanto MCP server and DCC-MCP Core MCP server.
How does Lm compare with other AI and agents MCP servers?
safety score 85/100 (higher than 75% of 4,456 AI and agents servers); tools 8 (the typical AI and agents server has 7); tools that change things 25% (typical: 3%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Lm

Same job from other publishers: the closest match first, then the best rated.

  • freellmpool
    OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.
    A
  • Memanto
    MCP server for Memanto - persistent semantic memory for any MCP-compatible agent
    A
  • DCC-MCP Core
    Agent control plane for DCC and engine hosts: one MCP endpoint, one tool contract.
    A
Lm vs freellmpool

More from houtini-ai →