"Resources for Frontend Coding" matching MCP servers:

A comprehensive MCP server for frontend analysis. It provides Google Lighthouse audits, code quality checks, SEO metadata verification, accessibility analysis, and bundle optimization for React and Next.js projects.

Enables AI tools to interact with browsers for enhanced frontend development, providing context to LLMs through tools like API call analysis, screenshots, element selection, and documentation ingestion.

Enables frontend navigation and browser automation through a deterministic MCP server, integrating Browser Use and optional code graph hints for coding agents.

Delegates frontend/UI refinement to Gemini via agy CLI, using iterative vision loops and diff-gating to realign UIs to design mockups without affecting backend code.

TypeScript implementation of an MCP server that provides tools for web crawling, content extraction, and browser automation, enabling AI systems to access and process web content through 15 specialized tools.

Enables coding agents to visually verify front-end changes by capturing screenshots at real breakpoints, identifying the single element responsible for overflow, and surfacing console and network errors.

Exposes a project's Reado code-review annotations (tasks, comments, reading progress, bookmarks) as MCP resources, plus tools for an AI coding agent to resolve review tasks, drive guided pair reviews, and inspect Reado's live browser preview.

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

A fault-tolerant, stealth-enabled Model Context Protocol (MCP) server for web searching and content fetching. Built for AI Agents (Cursor, Claude Code, OpenCode), it uses a stealth browser engine to fetch pages, dynamically handles SPAs/React, and converts bloat into token-optimized Markdown.

Gives AI coding agents a ten-phase frontend design pipeline (audit, style direction, build, review, verify, perf, brand) with an exclusive style menu. Its verify_page tool loads a URL in a real Playwright browser at mobile and desktop viewports and returns screenshots, ARIA snapshots, console errors, failed requests, horizontal-overflow offenders, axe-core violations, and pointer type.

Gives Claude control of a real, headed Chromium browser via Playwright, enabling web navigation, clicking, typing, screenshots, and JavaScript evaluation.

Provides a local MCP server for AI-powered web crawling on Windows, enabling agents to directly crawl and extract web content without requiring WSL.

Enables AI-powered music generation and live coding by providing direct control over Strudel.cc through browser automation. Supports pattern creation, audio analysis, and pattern storage for TidalCycles/Strudel music patterns.

A lightweight MCP server to control Arc Browser on macOS, optimized for frontend development with 30 tools including DOM operations, debugging, and network monitoring.

Enables comprehensive web frontend debugging and analysis through DOM inspection, JavaScript execution, network monitoring, console log capture, and automated browser interactions. Supports complete web development workflows including testing, data extraction, and performance analysis.

Enables agents to search and read posts, images, and limited comments across Xiaohongshu, Weibo, Zhihu, and WeChat Official Accounts, with local OCR and traceable sources.

A Model Context Protocol server that provides web search capabilities using Google Custom Search API and webpage content extraction functionality.

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

A CDP-native MCP server that lets AI agents drive a real Chrome browser with deep network/console inspection, robust page interaction, and the ability to reverse-engineer a site's API flow into runnable code with dependency chaining and replay verification.

Web scraper and token compressor that converts HTML to clean markdown with 70-80% fewer tokens. Single-page compression and multi-page BFS crawling with auto-fallback fetch modes.