"User interface design or related topics" matching MCP servers:

Searches design platforms for UI references and extracts design tokens such as colors, typography, spacing, and shadows from live websites.

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

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

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

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.

Enables end-to-end testing of voice-enabled web applications by simulating a synthetic user with a virtual microphone, virtual speakers, a real browser, and a viewable display, allowing audio injection, speech capture/transcription, and browser automation.

Perplexity AI search, reasoning, research, and compute - MCP server, dashboard, and multi-IDE auto-config for VS Code.

This MCP server provides a unified search experience by integrating and intelligently fusing results from multiple major search engines. It automates complex processes like query language detection, weighted result ranking, and engine failover to deliver robust and high-quality search output.

Enables AI clients to read design pages, screenshots, original assets, styles, and workflows from Lanhu, Figma, and Mockplus, inspect elements, download resources, and build local page-flow maps.

Enables automated product management on Shopee, TikTok Shop, and Lazada by controlling an existing Chrome or Edge browser session, intercepting internal APIs for fast updates, and pausing for captcha resolution.

Enables agents using Computer Use to inspect expected browser JavaScript dialogs and respond to OK/Cancel confirmations or text prompts without user intervention. Unexpected dialogs still interrupt the workflow.

Web Content Retrieval (full webpage, filtered content, or Markdown-converted), Custom User-Agent, Multi-HTTP Method Support (GET/POST/PUT/DELETE/PATCH), LLM-Controlled Request Headers, LLM-Accessible Response Headers, and more.

Enables AI agents to run live Google searches and retrieve organic results, snippets, sitelinks, People Also Ask, related searches, and Google's AI Overview with citations via a zero-dependency MCP server.

Enables browsing the 4PDA forum through MCP tools for listing forums, topics, and posts using the lightweight lofi text version, with built-in rate-limit handling.

AI design fidelity — compare Figma designs or screenshots against the rendered implementation and get structured discrepancies. Uses your Claude Code or Codex subscription, no API keys.

MCP server that provides automated Google search capabilities, allowing query execution, result limiting, and optional related keywords retrieval.

A powerful Model Context Protocol (MCP) server for scraping Behance.net. Extract projects, user profiles, images, and job listings from Behance's creative community without any API keys or subscriptions.

This MCP server helps debug legacy devices behind proxies in OT environments by analyzing web interfaces and generating custom rewrite rules to fix proxy-related issues.

Enables querying and aggregating Chinese and international news along with multi-platform trending topics, featuring deduplication, event clustering, and article extraction for AI clients.

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.

Enables AI agents to automate a browser-based kinetic typography and video editing interface, including loading lyrics, choosing styles, setting BPM, clicking controls, capturing previews, and exporting MP4 or transparent PNG sequences.

Enables AI agents to control the user's Chrome or Firefox browser, leveraging existing sessions for tasks requiring authentication and user handoff.

A local MCP server for semantic search over RSS/Atom feeds, providing tools for ranked search, trending topics, digests, and feed health monitoring without requiring an API key.

Enables searching and reading linux.do Discourse forum content, including topics, categories, tags, and user info, using a login cookie for trusted access.

Enables agents to read, write, format, fill, and export Google Docs and Slides as the signed-in user through a real Chrome browser, without API keys or OAuth.

Drives the real Claude Design web app from your editor or agent, enabling creation, iteration, and retrieval of designs generated on your own claude.ai account via automated browser interaction.

Enables MCP agents to drive an already signed-in Chrome or Edge browser through a local extension bridge, controlling existing tabs and opening task-related HTTP(S) tabs without remote debugging or profile copying.

Enables coding agents to discover live visual design references, inspect original sites as MCP images, analyze elements and motion, and verify implementation constraints during an original design workflow.

Enables LLMs to autonomously retrieve and explore web content by fetching pages and recursively following links to a specified depth, particularly useful for learning about topics from documentation.

A human-in-the-loop browser MCP server that pauses for user actions like login or CAPTCHA, saves and reuses authentication contexts, and extracts page data for development assistance.