io.github.houtini-ai/lm
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to
Before you connect
Config example (to connect)
{
"mcpServers": {
"houtini-lm": {
"command": "npx",
"args": ["-y", "@houtini/lm"],
"env": {
"HOUTINI_LM_ENDPOINT_URL": "http://localhost:1234"
}
}
}
}Works with these clients
- Claude Desktopnpx
- Claude Codenpx
- Cursornpx
- VS Codenpx
- Windsurfnpx
Derived from the registry manifest (package type and transport) — we have not installed it ourselves. Check the official README before relying on it.
Install / Connect
claude mcp add lm -- npx -y @houtini/lm@3.2.3Follow the official README; env and args vary per server.
🛠️ Maintenance weight 30% · 82 pts
📊 Adoption weight 25% · 47 pts
✅ Usability weight 20% · 100 pts
❤️ Health & community weight 25% · 59 pts
Sources: GitHub API · npm registry · Official registry · updated 2026-08-10
90-day trend
⭐ stars +2%
📦 weekly downloads +0%
Similar / alternative servers
io.github.ZahiriNatZuke/local-delegate
Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude q
io.github.HUANGCHIHHUNGLeo/claude-real-video
Let any LLM watch a video locally — and search everything it has ever watched.
io.github.Lykhoyda/ask-llm
Unified MCP server — auto-detects Gemini, Codex, Claude, Ollama, and Antigravity
io.github.eralpozcan/vision-squeezer
Cut vision-LLM token costs by snapping images to tile boundaries — Claude, GPT,
One email a week, 5 minutes to see what happened in the MCP ecosystem
New servers, breakout trends, abandonment alerts — tracked automatically, curated by hand, sent to your inbox.
One email a week · unsubscribe anytime · no data selling