Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
Deterministic AI data-center design engine exposed as MCP tools (design, validate, layout): rack count, design PUE, total MVA, liquid/air cooling split, CDU planning, cost & timeline. NVIDIA Rubin-era, 22.9 kV intake, Korea. Remote Streamable HTTP at https://aidc-ai.io/api/mcp; no key for the anonymous tier.
Catch bad animations before they ship. 13 deterministic checks on the live page (duration, easing, stagger, exits, reduced-motion, touch-gated hover) with no API key or LLM, plus optional vision-LLM UX review across viewports. Install via NPM: npx -y motionlint mcp
Quality signal
45/100 (Fair)
41/100 (Fair)
Install path
Remote · high
npx · high
Engagement
2 0 0 3
0 0 0 0
Tools
Design AI data centers with rack count, PUE, power, cooling, cost, and timeline outputsValidate designs for compliance with electrical, cooling, layout, and safety standardsGenerate rack-plan grids and site-block layouts with row/column positions in millimetersSupports NVIDIA Hopper, Blackwell, and Rubin-era GPUs with Korean site constraintsAccessible via Streamable HTTP MCP endpoint and REST API without authentication for anonymous tier
