"Material Design" matching MCP servers:

Translates design tokens across platforms — extracts from Tailwind/CSS/Figma and generates native themes for Material 3, SwiftUI, and CSS variables with WCAG contrast validation.

Enables AI agents to manage routes on the Design Canvas infinite canvas app, including adding, removing, listing routes, and capturing screenshots of the canvas.

Design contract layer for AI agents. Scans Figma, code, Storybook, and token files, reconciles conflicts, and serves a single machine-readable source of truth so every agent gets the same authoritative design rules before it builds. Local-first.

Manages design tokens (colors, spacing, fonts) in a JSON file and enables agents to read, write, export, and detect drift between tokens and CSS via MCP.

Provides read-only access to over 100 UX/UI design checklists from Checklist.design, enabling users to search and retrieve design guidance for specific flows and screens. Runs locally without an API key.

Enables AI coding agents to retrieve mode and stage guidance so they can lead users through a 9-stage design workflow, including questions, required artifacts, exit criteria, dependencies, pitfalls, rollback impact, and environment requirements. It helps non-designers turn ideas into buildable HTML/WPF design specs while keeping the human in control of confirmation and revisions.

Enables high-craft web design and engineering through OKLCH color systems, fluid typography, Three.js 3D scenes, frontend security audits, multi-viewport capture, and Python-backed design verification.

Provides software design guidance via MCP, including SOLID principles, design patterns, pattern scaffolding, and heuristic code-smell detection to help review and refactor code.

Enables AI coding agents to search public design-system catalogs and retrieve only the relevant tokens or sections for a chosen brand, so generated UI matches a specified visual style instead of generic AI output.

Provides design pattern templates and anti-pattern guidance to AI coding agents for correct pattern implementation.

Provides deterministic design style recommendations and structured tokens for AI content generation, with 30 curated styles including color palettes, typography, and visual directives.

A local-first FastMCP server that indexes offline frontend catalogs (components, patterns, motion libraries) and exposes discover, search, compare, and recommend tools to AI agents via stdio.

Enables AI assistants to retrieve and cite South Korean national construction standards (KDS/KCS) with tables and formula images via the KCSC OpenAPI, and to use design decision trees, validation, and blank Excel templates directly in the chat interface.

A local stdio MCP server that enables AI coding tools to search and retrieve reusable interactive and motion design parts from a design-notes library, returning each part's notes, anchors, extracted parameters, and the absolute path to its self-contained index.html source. It also serves the original README provenance and source URLs for a given note.

Generates randomized English Markdown frontend design directions using curated catalogs, with optional soft compatibility scoring. Does not call an LLM.

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.

Bridges Claude Code with Claude Design, enabling sending design instructions, reading replies, and pulling generated files into the codebase.

Provides AI assistants access to live Material Design 3 documentation including Foundations, Styles, and Components, returning official content as Markdown.

A local MCP server for AI image generation using ComfyUI, Claude Code, and OpenClaw, with a built-in library of over 1,300 prompts for private, fast image creation.