"Material Design Icons" matching MCP servers:

Converts any rendered web page into a complete, LLM-readable design specification—including block screenshots, distilled computed CSS, design tokens, responsive deltas, and alpha-channel-analyzed assets—so models can accurately reproduce the design.

AI-native design engineering platform that converts Figma or live websites into a semantic design graph for code generation, and generates Figma designs from prompts with a self-improving director loop.

A stateless MCP server for UI/UX design inspiration, live component discovery, and modern web micro-effects, resolving queries in real time via the Serper API.

Searches top design platforms like Dribbble and Behance to provide UI inspiration, color palettes, and layout patterns via the Serper API. It allows users to retrieve visual references, articles, and style guides directly within any MCP-compatible client.

MCP server that gives AI agents browser-based access to Mobbin for design research, screen discovery, and screenshot collection through automated browser control.

Enables assistants to discover, search, and extract real design systems — palettes, type scales, spacing, surfaces, and do/don't guidance — from the public style pages of styles.refero.design. It reports index coverage with every search and renders matched styles as structured design.md sections or parsed JSON tokens.

Enables evidence-grounded web design analysis by searching GDWEB references and generating isolated, per-reference DESIGN_INDEX specification documents for LLM-driven frontend development.

MCP server that scrapes Terminal Trove to search CLI/TUI tools and retrieve design references like screenshots and install commands for agentic UI research.

Enables AI agents to keyword-search and browse curated UI/UX design inspiration — landing pages, iOS apps, and website templates — and view full-page or per-section screenshots without needing an API key.

One-click website design cloning with Puppeteer. Captures HTML, CSS, colors, fonts, and layout structured data for recreation.

Compares Figma frames to live pages, checking colors, fonts, and border radii, and generates a shareable HTML report.

Provides AI agents with a visual design inspiration loop from award-winning websites, including natural-language search, inline screenshots, and detailed design DNA extraction. Also supports optional live page capture, structure analysis, and motion recording for design verification.

Automatically generates complete favicon sets from PNG images or URLs, creating multiple sizes, ICO files, Apple touch icons, and manifest.json for web applications.

MCP server and CLI for EVA FING (Moodle of Facultad de Ingeniería, UdelaR) that authenticates headlessly via Shibboleth, enabling AI agents and users to query courses, announcements, activities, calendar, and study material.

Captures webpage styles and HTML, converts CSS to Tailwind, and applies extracted designs to frontend frameworks like React.

Web design analysis MCP server with 20 tools for layout extraction, motion detection, quality scoring, and semantic search. Uses Playwright, pgvector HNSW, and Ollama Vision to turn web pages into searchable, structured design knowledge.

A Model Context Protocol server that analyzes webpage design structures, providing detailed layout, navigation, content, form, image, and link information from a given URL.

Advanced Model Context Protocol server that integrates Gemini AI with Tailwind CSS, providing intelligent component generation, class optimization, and cross-platform design assistance across major development environments.

An intelligent website logo extraction system built on the Model Context Protocol (MCP) that automatically identifies and extracts logo icons from websites.

Intelligently extracts and analyzes website logos from multiple sources (favicon, Apple Touch icons, OpenGraph, CSS) with automatic quality scoring and format support. Provides detailed logo information and returns the best logo URL for any given website.

Extract design tokens, colors, typography, spacing and components from any live website, and compute design drift against an approved baseline. Exports DESIGN.md, DTCG, Tailwind and shadcn.

An MCP server for web intelligence extraction that provides 55 tools for extracting structured data, design systems, accessibility audits, and more from websites.

MCP server for the MiroMiro design-extraction API. It extracts real design data from live websites—including brand colors, fonts, tokens, SVGs, images, and component code—so AI agents can build from actual values.

MCP server for extracting UI components, design tokens, and patterns from websites and generating production-ready React, Vue, and HTML components.

Open-source technical SEO crawler MCP server built on LibreCrawl. Runs full audits inside Claude, Cursor, or Codex — 50+ checks (hreflang, schema.org, security headers, WAF detection on 200-OK pages), chunked-progressive engine for large sites, ephemeral by design (server forgets every audit after download).

Enables browsing and reading curated design and photography feeds, as well as fetching any RSS/Atom/RDF feed with robust fallback.

Provides live Awwwards design specifications—palette, typography, layout, and motion—as structured JSON tokens that Lovable or any MCP client can use to generate or restyle projects on demand.

Enables AI assistants to extract design systems, brand guidelines, copy, and sitemap structure from any live website via the Pastebase API.

Enables agents to turn web pages into sectioned, token-counted Markdown and read only the chunks needed, with tools for outlines, manifests, splits, and design-token extraction.

A stdio MCP server that enables coding agents and browser-use pipelines to distill bloated DOM and UI context into token-budgeted Tailwind v4 HTML, React JSX, GFM tables, design tokens, or structured AI prompts.

Turns any URL into structured web intelligence in one call: SEO/OpenGraph metadata, public contacts, tech-stack fingerprinting, Schema.org data, a security-headers audit, and clean AI-ready Markdown. Anti-SSRF hardened by design.

Enables coding agents to search and retrieve real production websites, their design systems, and reference components over MCP, so they can study design patterns before writing UI.

Enables AI assistants such as Claude, ChatGPT, Cursor, and Claude Code to run 25+ specialized SEO checks on any URL, generate XML sitemaps and robots.txt files, extract brand design elements, and audit technical SEO, content quality, mobile responsiveness, and security.

Enables AI coding assistants to query, search, and preview curated real-world navigation bar components, injecting design inspiration directly into coding sessions.

Gives Claude the ability to inspect and extract UI components from any webpage through a Chrome extension, enabling element discovery, style extraction, and design token analysis.

Enables agents to collect posts and visible comments from specified X accounts, building unique profiles and analyzing publishing cadence, content style, and high-engagement material, with resumable pagination and CSV/JSONL export backed by PostgreSQL. Supports bounded failover across multiple configured accounts and opt-in hourly monitoring of new posts, edits, and visibility changes, reporting only when asked.

MCP server that extracts accessibility tree, design tokens, screenshots, Claude DSL, and Figma JSON from any URL using a persistent Chromium browser with zero LLM cost.

Enables Claude Desktop to connect to Anthra Studio for AI-powered web design generation and multi-page suite management via the Model Context Protocol.

Reads the design system of any live website in a real browser and exposes it to the editor as W3C DTCG design tokens, a Tailwind config, CSS variables, a shadcn/ui theme and Figma variables. Also scores how generic a page looks and checks AI-built UI against your brand.

Enables developers to search and retrieve captured UI and interaction cases by their intended purpose during coding sessions, making reproduced design references directly available to coding agents.