aidc-ai
aidc2026ai-melon/aidc-ai-mcp
Deterministic AI data-center design for Korea (NVIDIA Rubin era, 22.9 kV intake): rack count, PUE, total MVA, cooling split, CDU planning, cost and timeline.
- Official
- Cloud integrations
Installation, supported tools and required credentials are maintained by the project.
Project details
- GitHub stars
- 3
- Language
- JavaScript
- License
- MIT
- Forks
- 0
- Latest release
- v0.1.03mo ago
- Activity
- updated 24d ago
- ai-datacenter
- cdu
- datacenter
- korea
- liquid-cooling
- mcp
- model-context-protocol
- nvidia-rubin
First MCP server?Start with the basics
Draw cloud architecture diagrams with the official AWS, Azure and GCP icons from a plain description, a JSON graph or Terraform code, with VPC, subnet and zone grouping. PNG, SVG and editable draw.io output.
Bidirectional Figma bridge: turn selections into framework-aware code reusing your components and tokens, or create frames, text, styles, variables and screens.
Construction plan takeoff: load plan PDFs, read title blocks, set drawing scale, trace rooms and export quantities like square footage and linear feet.
Local-first network design: create Cisco-style network master files, L1/L2/L3 topology diagrams, HTML viewers, device tables and AI context files.
Generate Excalidraw architecture diagrams with auto-layout, technology-aware component styling (databases, queues, caches) and stateful editing.
Text language for human movement that LLMs can write, rendered as an anatomically constrained 3D human figure in the browser.
Mermaid diagram generation (flowcharts, sequence, class, ER, architecture and state diagrams) with templates, layout engines and SVG/PNG/PDF export.
Local design engine: create, edit and export branded social posts, flyers, decks and business cards, with print-ready PDFs and InDesign, PSD and PDF import.