INSANE0777/Awwwards-mcp

Free, open-source MCP server that gives AI coding agents (Claude Code, Codex, Cursor, OpenCode, ZCode…) design inspiration from award-winning websites — search with real screenshots, pull design DNA, capture and record live sites. A Mobbin alternative. No API key.

What it solves

This project provides AI agents with the ability to source high-quality design inspiration and technical blueprints from Awwwards. It bridges the gap between seeing a beautiful website and understanding exactly how it was built, allowing agents to analyze, recreate, and verify complex web designs.

How it works

It functions as an MCP (Model Context Protocol) server that connects to your coding agent. It uses a combination of live scraping and a local SQLite index to search for websites by color, tag, or technology. Once a site is selected, the agent can perform deep forensics: mapping page structure, recording motion (scroll/hover animations), fingerprinting the tech stack, and even capturing 3D canvas poses. Finally, it can convert these findings into a functional Vite, Astro, or Next.js project and verify the build quality against the original site.

Who it’s for

It is designed for developers using AI coding agents (such as Claude Code, Cursor, or Cline) who want to build high-end, motion-rich websites and need a systematic way to study and replicate professional design patterns.

Highlights

  • Design DNA Extraction: Pulls color palettes, tech stacks, and award history for any site.
  • Motion Forensics: Captures scroll-triggered animations, hover interactions, and GSAP timelines from live URLs.
  • Automated Rebuilds: Converts analyzed page structures into ready-to-run framework projects.
  • Verification Engine: Scores your build against the reference site using band-map comparisons and motion-fingerprint diffs.
  • Universal Tooling: Most analysis tools (capture, census, verification) work on any URL, not just Awwwards winners.
  • Offline-First: Operates without API keys or accounts, using a local SQLite cache for fast, reliable data access.

Related

  • Project
    GeorgesAlkhouri/nvim-aider

    A Neovim plugin that integrates the Aider AI pair programmer, enabling users to send buffers, diagnostics, and files to the AI directly from their editor.

  • Project
    dirge-code/dirge

    A minimal, fast coding agent written in Rust that uses a two-tiered memory system and lexical search to maintain long-term project continuity across sessions.

  • Project
    databricks/databricks-agent-skills

    A collection of skills and plugins that provide AI coding agents with specialized knowledge and guidance for building and managing resources on the Databricks platform.

  • Project
    mc3545dada/mspm0-skill

    A set of rules and scripts that enable AI Agents to configure, build, flash, and debug TI MSPM0 microcontrollers by directly interacting with SysConfig and hardware toolchains.