houtini-lm (houtini-ai/houtini-lm) is an MCP server listed on the M8ven Trust Index. It scores 89 out of 100, grade B. It declares 8 tools. No publisher has claimed this listing.

Emerging

89/100

1 month ago

houtini-lm

Item: houtini-lm
Rating: 89
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

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

houtini-ai

Source: github_topic · also listed on modelscope

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. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHub modelscope

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.

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

🔐 secretHOUTINI_LM_API_KEYe =your-key-here \

configHOUTINI_LM_CONTEXT_WINDOW100000 Fallback context window if the API doesn't report it. Legacy alias: LM_CONTEXT_WINDOW.

configHOUTINI_LM_CROSS_PROCESS_LOCK1 Set to 0 to disable just the cross-process inference lock (keeps the in-process semaphore).

configHOUTINI_LM_ENDPOINT_URLclaude mcp add houtini-lm -e =http://192.168.1.50:1234 -- npx -y @houtini/lm

configHOUTINI_LM_FILE_ROOTS(unset) Optional :/,-separated allowlist of directory roots code_task_files may read from (symlink-resolved). Unset = any absolute path.

configHOUTINI_LM_MAX_FILE_MB10 Per-file size cap for code_task_files.

configHOUTINI_LM_MIN_TOKENS

configHOUTINI_LM_MODELe =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.

configHOUTINI_LM_SERIALISE

configHOUTINI_LM_THINKING

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

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

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

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

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

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

configPIN_MODEL

configVLLM_URL

// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

8/8 tools missing one or more hints — chat (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); custom_prompt (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); code_task (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +5 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tests exist

No test files found

Add tests that exercise each declared tool.

Shell command execution

9 child_process calls — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 4 concrete improvements 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)](https://m8ven.ai/mcp/houtini-ai/houtini-lm)

Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.

commit: d9871cb86dcd7e75de5e6a3f1a317f688f26f823

code hash: 38040349ed12fa8abe3658436a375e6f0659343dbdde88ff68178f8f1dcc5bf2

verified: 8/7/2026, 2:19:20 AM

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client