"Automating Testing and Debugging for LLMs in Production" matching MCP servers:

Code-aware browser testing agent — reads your codebase, understands functionality, tests every element, reports with screenshots. Works as MCP server for Cursor/Claude Code or standalone CLI.

Controls a running Chrome/Chromium browser via the Chrome DevTools Protocol, enabling navigation, JavaScript evaluation, tab management, and raw CDP commands through MCP tools.

Enables accessibility testing of websites and HTML content using axe-core and IBM Equal Access engines. Supports WCAG compliance checking, multi-viewport testing, and provides detailed violation reports with remediation guidance.

Enables AI agents and MCP clients to drive real Chrome, Edge, Brave, and Firefox browsers through native automation protocols. It exposes tools for navigation, page snapshots, form filling, clicks, screenshots, console/network inspection, and tab management.

Enables MCP clients to open websites, capture screenshots at multiple breakpoints, and run automated design audits for issues like overflow, small tap targets, low contrast, missing alt text, tiny text, and clipped content.

Enables AI agents and MCP hosts to drive a persistent headless Chromium browser through Playwright, navigating pages, mapping visible fields and actions, clicking, typing, scrolling, and capturing screenshots via stdio tool calls. It also powers a local AI Test Studio dashboard that generates and runs structured end-to-end test plans with assertions, per-step timing, and screenshot evidence.

Enables Claude Code to control Firefox through tools for tabs, navigation, clicks, typing, scrolling, screenshots, page reading, forms, JavaScript, and console/network logs.

Enables any MCP client to drive the user's real Chrome profile through a Chrome extension bridge, with tools for navigation, accessibility snapshots, ref-based interactions, console/network reading, screenshots, tab management, and restricted script evaluation.

Enables AI agents to test Telegram bots by driving the official Telegram Web client in a real browser, allowing visual verification of bot responses, inline keyboards, and Mini Apps.

Exposes browser-testing capabilities—including navigation, clicking, typing, form submission, verification, and screenshots—so clients can discover the supported Playwright actions. It also builds structured testing requirements from a supplied website and task description, ready for plan generation and execution.

DREAM LAUNCHERS INTERIORS PRIVATE LIMITED

Enables reading and sending messages in Google Messages for web through a paired Chrome tab using chromefile, with tools for status, listing conversations, reading message history, and sending texts.

Enables AI agents to perform comprehensive web application testing including visual, functional, performance, accessibility, and SEO analysis using browser automation without requiring API keys.

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.

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

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.

Enables AI agents to drive real Google Chrome with stealth and captcha handling, using Patchright to avoid bot detection.

Enables ZCode to control a real Chrome browser, including tabs, navigation, page content, clicks, form filling, keyboard input, scrolling, screenshots, and JavaScript evaluation through a local MCP bridge.

MCP server for AI agents -- fetch any URL with full JavaScript rendering (Playwright/Chromium) and convert to clean, token-efficient markdown. Works on React, Vue, Angular, and any JS-heavy page. Includes web search, batch fetching, binary file download, LRU cache, SSRF protection, and structured output.

MCP server that gives AI agents access to current web information through web_search and fetch_url tools, using Tavily, Brave, and DuckDuckGo providers with automatic fallback.

A local testing tool for APIs, web browsers, and phone UI using the Model Context Protocol.

Enables automated browser testing of web applications using Playwright, supporting user interactions, form submissions, console monitoring, network request inspection, and visual verification through screenshots.

Enables crawling sites from start URLs and retrieving internal and external links, file download links, HTML tables as rows, and lists, with controls for crawl depth, page limits, sitemaps, robots.txt, and proxy mode.

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.

Enables AI agents to manage live Firefox tabs and native tab groups via MCP tools over stdio, with exact-match verification and safety constraints. It does not read page content or send browser data remotely.

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 lightweight MCP server for browser automation using Playwright with essential tools for navigation, form interaction, and web scraping. Provides 16 core browser automation tools with minimal setup and fast performance.

A server that helps discover and analyze websites implementing the llms.txt standard, allowing users to check if websites have llms.txt files and list known compliant websites.

Enables AI agents to create, validate, and audit llms.txt files for websites, including checking against Google Lighthouse's Agentic Browsing requirements, via Streamable HTTP with no API key needed.

Enables Claude Code to drive a real Firefox browser through a local MCP server using synthetic DOM events for clicks and typing. Supports tab management, navigation, page reading, form interaction, screenshots, and per-site consent with no network port opened.

Maps Electron app IPC handlers to MCP tools and provides 33 built-in CDP tools for DOM automation, screenshots, interaction, and debugging, enabling Claude Code to directly control your Electron app.

Enables local opencode agents to control a live Chrome browser via MCP tools, including tab management, JavaScript execution, clicking, form filling, page reading, screenshots, and console log retrieval.

Enables AI agents to control a Playwright-driven browser through natural-language instructions, including page interaction and live browser task execution.

Enables Claude Code to control the user's real Firefox browser through a local MCP server, with tools for tabs, navigation, page reading, clicking, typing, forms, screenshots, and file uploads under per-site consent.

Lets coding agents and MCP clients read, navigate, and interact with pages in the user's already signed-in Firefox through background tabs, without touching or stealing focus from the tab being viewed.

Enables AI agents to extract, validate, and discover documentation from websites using llms.txt and install.md standards.

Enables AI assistants to control the Comet browser via Chrome DevTools Protocol, supporting navigation, interaction, form automation, and debugging with multi-client and WSL compatibility.

Classifies company sites as B2B or B2C and as SaaS, online store, agency, manufacturer, wholesaler, distributor, or marketplace, while matching your own buyer phrases and returning the quoted text and page as evidence. Runs deterministically on Apify, giving one row per domain with grace-free status rows for unreachable, blocked, or empty sites.

Give it a product and a country and it searches Google for manufacturers, wholesalers, and distributors, reads each candidate company's own website, and returns only the ones whose pages back up the claim, with quoted evidence, the domain, and a confidence score. Directories, marketplaces, and social networks are filtered out, and a free summary row reports how many sites were found and checked when nothing qualifies.