Developer · Local MCP server

Lm

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

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.houtini-ai/lm
Version
3.3.3
Status
Active
Category
developer
Transport
stdio (local process)
Package
npm
Published
2026-09-24
Updated
2026-09-24
Publisher
houtini-ai (GitHub) · 8 servers with pages here
Listed under
OpenAI MCP servers
Repository
github.com/houtini-ai/houtini-lm
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
npm@houtini/lm3.3.3stdioHOUTINI_LM_ENDPOINT_URL, HOUTINI_LM_API_KEY (secret), HOUTINI_LM_MODEL, HOUTINI_LM_PROVIDER

How to connect Lm

Lm runs locally from a Node.js package published to the npm registry: @houtini/lm version 3.3.3. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y @houtini/lm@3.3.3. It reads these environment variables: HOUTINI_LM_ENDPOINT_URL, HOUTINI_LM_API_KEY (secret), HOUTINI_LM_MODEL and HOUTINI_LM_PROVIDER; set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "lm": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/lm@3.3.3"
      ],
      "env": {
        "HOUTINI_LM_ENDPOINT_URL": "<value>",
        "HOUTINI_LM_API_KEY": "<secret>",
        "HOUTINI_LM_MODEL": "<value>",
        "HOUTINI_LM_PROVIDER": "<value>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More from houtini-ai (GitHub)

All 8 →
ServerRunsEndpoint or package
Amazon CreatorsAmazon product search returning paste-ready affiliate deal rows for your blog.Local · stdionpm: @houtini/amazon-creators-mcp
FanoutMulti-URL comparative content analysis with topical gap detection.Local · stdionpm: @houtini/fanout-mcp
FmpAccess financial data and market information via Financial Modeling Prep API.Local · stdionpm: @houtini/fmp-mcp
Geo AnalyzerScores content on the signals that get it cited by ChatGPT, Perplexity and AI Overviews.Local · stdionpm: @houtini/geo-analyzer
Google Knowledge GraphSearch Google's Knowledge Graph for structured information about real-world entities.Local · stdionpm: @houtini/google-knowledge-graph-mcp
Seo Audit ConsoleTechnical SEO in Claude: GSC + crawl + DataForSEO - audit, market sizing, content recon.Local · stdionpm: @houtini/seo-audit-console
Seo Crawler MCPCrawl and analyse websites for SEO errors using Crawlee with SQLite storage.Local · stdionpm: @houtini/seo-crawler-mcp

More developer servers

All 6,250 →
ServerRunsEndpoint or package
LlmgraphInvoke deployed LLMGraph no-code LLM workflows (chat, RAG, automations) as MCP tools.Local · stdionpm: @llmgraph/mcp-server
LlmrefVersioned documentation registry and semantic search for AI tools and coding assistants.Remote · HTTPapi.llmref.org
Llmtest MCPBenchmark AI models on real prompts. Find cheaper, faster alternatives across 340+ models.Local · stdionpm: llmtest-mcp
llmtrimMCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.Local · stdionpm: @llmtrim/cli
LoadbenchMCP server for structural load & stability math: tipping, support reactions, beam checks.Local · stdioPyPI: loadbench-mcp
LoaditoutSearch and install 20,000+ security-graded MCP servers and agent skills.Local · stdionpm: loaditout-mcp-server
LoadsterLoad testing and synthetic monitoring platform: test with Playwright, Browser Bot, or Protocol Bots.Remote · HTTPapi.loadster.com
Local FAISS MCP ServerLocal FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.Local · stdioPyPI: local-faiss-mcp