houtini-lm

Item: houtini-lm
Rating: 74
Author: M8ven

MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.

→ houtini-ai/houtini-lm · listed on github_topic

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.

Install from

GitHub

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings

✅

No credential exfiltration, no sensitive file access, no obfuscation

Static analysis found nothing flowing your secrets to unexpected places.

✅

Open source with a license and README

Anyone can audit the code, the license is declared, and the publisher documents what it does.

🔐

You'll be asked for 4 credentials: HOUTINI_LM_API_KEY, LM_PASSWORD, LM_STUDIO_PASSWORD, OPENROUTER_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// required environment variables

This server reads these from process.env. You'll be asked to provide them before it can run.

🔐 secretHOUTINI_LM_API_KEY— e =your-key-here \

configHOUTINI_LM_CONTEXT_WINDOW— 100000 Fallback context window if the API doesn't report it. Legacy alias: LM_CONTEXT_WINDOW.

configHOUTINI_LM_ENDPOINT_URL— claude mcp add houtini-lm -e =http://192.168.1.50:1234 -- npx -y @houtini/lm

configHOUTINI_LM_MODEL— e =nvidia/nemotron-3-nano-30b-a3b:free \

configHOUTINI_LM_PROVIDER— (auto-detect) Force provider-specific handling. Set to openrouter for OpenRouter attribution headers, reasoning.exclude, and no inference serialisation. Otherwise auto-detected from the endpoint URL.

configLM_CONTEXT_WINDOW— HOUTINI_LM_CONTEXT_WINDOW 100000 Fallback context window if the API doesn't report it. Legacy alias: .

🔐 secretLM_PASSWORD— HOUTINI_LM_API_KEY (none) Bearer token for authenticated endpoints. Legacy aliases: LM_STUDIO_PASSWORD, , OPENROUTER_API_KEY.

configLM_STUDIO_MODEL— HOUTINI_LM_MODEL (auto-detect) Model identifier — leave blank to use whatever's loaded. Legacy alias: .

🔐 secretLM_STUDIO_PASSWORD— HOUTINI_LM_API_KEY (none) Bearer token for authenticated endpoints. Legacy aliases: , LM_PASSWORD, OPENROUTER_API_KEY.

configLM_STUDIO_URL— HOUTINI_LM_ENDPOINT_URL http://localhost:1234 Base URL of the OpenAI-compatible API. Legacy alias: .

🔐 secretOPENROUTER_API_KEY— HOUTINI_LM_API_KEY (none) Bearer token for authenticated endpoints. Legacy aliases: LM_STUDIO_PASSWORD, LM_PASSWORD, .

configPIN_MODEL

// full audit trail

The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.

// improvement guidance — verified publishers only

We have 1 concrete improvement we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Score](https://m8ven.ai/badge/mcp/houtini-ai-houtini-lm-1r3ptm)](https://m8ven.ai/mcp/houtini-ai-houtini-lm-1r3ptm)

commit: 71d889e42abe70e8b6a06370f0cc9333dd378fd0

code hash: 8be0a1282be0328c7f09a0e3eaa0175abd0cf1ca55da0f62a9c6a88993dc5541

verified: 6/14/2026, 10:54:03 AM

view raw JSON →