VUDA: Visual UI Debug Agent - An autonomous MCP for visual testing and debugging of user interfaces

Highly configurable YATT MCP server library: spin up your own UI-testing MCP server (35 tools, Playwright engine, headless-first) with strict, typed configuration for paths, HTTP transport, auth, permissions, sessions and retention.

The fastest MCP server for iOS development. 49 tools free, one Swift binary, zero dependencies. xcresult parsing, WDA UI automation, structured test results.

SceneScout — exploratory UI testing for AI coding agents. An MCP server that gives any agent (Claude Code, Cursor, VS Code Copilot, Codex, Gemini CLI and others) a structured view of a running web app, always-on oracles, a network-level write policy, memo

MCP server for the Web UI Component Specification — behavioral specs, tests, and principles for web UI component libraries

MCP server for the Web UI Component Specification — behavioral specs, tests, and principles for web UI component libraries

Generate realistic test data that follows your business rules. Offline, reproducible, independently verified, with safe manifest-based cleanup. CLI, terminal UI, web UI and MCP server. Java 21.

MCP server that lets AI see and operate Windows desktops (UI Automation + WebView2 via CDP) and replay saved scenarios for E2E tests. .NET 10.

Visual UI testing and debugging MCP server with Playwright, screenshots, DOM inspection, workflow validation, and visual diffs.

MCP server for Android — drive emulators and real devices over adb from Claude Code, Cursor, or VS Code. 73 tools: screenshots, UI hierarchy, tap/swipe/type, logcat, device locks, Gradle builds and tests. The Android counterpart to XcodeBuildMCP.

MCP server for the full iOS development lifecycle — 55 tools for building, testing, debugging, UI automation, and more. Native Swift binary.

Taichi is a language-agnostic, plugin-driven test orchestration framework — run API, gRPC, UI, static, and regression tests with one CLI, extend via third-party skill plugins in any language, integrate AI agents for auto-fix loops, and ship JUnit/JSON/HTML reports.

An MCP server that automatically fixes broken Selenium test locators when UI changes occur, reducing test maintenance overhead.

Human-like AI QA testing for any web app — Claude Code & Codex plugin, MCP server and CLI. Playwright drives a real browser like a person, finds UI, accessibility and permission bugs, and re-tests only what changed. Zero AI tokens per run.

A FastMCP server that exposes Jira + Zephyr Scale (test management) operations as MCP tools — so an MCP client (like Claude Desktop) can create, query, and audit test cases directly through natural-language calls instead of the Jira/Zephyr UI or REST calls.

Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.

AI-driven cross-platform UI automation engine with test script generation

MCP server with coding skills and subagents — debugging, code audits (correctness, security, best practices, SQL migrations), feature planning, testing (React/Vitest, Deno, pgTAP), UI/accessibility audits, deep research, and doc generation. Works with Cur

An MCP server that lets Claude Code use your Windows apps. It reads each window as text through the accessibility tree, presses, fills and selects controls through UI Automation without moving your mouse, and replies to every action with what changed. One exe under 200 KB, no admin rights, free (Apache-2.0). Tested on Windows 11 with Claude Code.

This project is a Java-based UI automation framework that integrates with Appium and utilizes LLMs (like Claude) to drive intelligent test actions on mobile devices and simulators.

A Model Context Protocol (MCP) server that supercharges Flutter Widgetbook development by giving AI assistants direct access to create, modify, and test UI components in your design system.

Terminal UI engine for Go that tests can click and AI agents can drive (MCP). Zero-allocation rendering, immediate mode + Elm architecture, 3D, images, charts, accessibility, WebAssembly.

This project implements a penetration testing and purple team AI-agent-driven server built with MCP and a Gradio UI frontend, designed to run as a Hugging Face Space.

scrcpy-mcp gives AI agents real vision and control over Android devices. It exposes screenshots, taps, swipes, text input, key events, UI inspection, and arbitrary ADB shell commands as MCP tools, so an agent can drive a phone or tablet the way a person would. When a scrcpy session is active, input and screen capture run 10–50× faster than plain ADB, making real-time automation, on-device testing, and UI agent workflows practical. Highlights - Fast screenshots and live screen capture - Tap, swipe, drag, long-press, scroll, and text input - UI hierarchy dump and element search by text, resource-id, or class - Arbitrary ADB shell command execution - Optional scrcpy session for low-latency control Works with any ADB-reachable Android device (USB or Wi-Fi). Configure ADB_PATH, ANDROID_SERIAL, and scrcpy paths as needed.

PicassoWeb MCP Server: An AI-agent tool for automated UI replication, CSS token extraction, and design system scraping via headless Chromium. Features pixel-differential testing, asset downloading, layout mapping, and component cloning.

A production-shaped Laravel 13 invoicing app whose entire feature surface (auth, tenancy, invoice lifecycle, PDFs) is also reachable over the Model Context Protocol, with an automated parity test proving every UI capability has an equally-policed MCP tool.

Let your coding agent test the real Windows UI: an MCP server and CLI that inspect your app, drive its controls, and run repeatable checks with screenshots and signed evidence. Also a free screenshot, annotation and recording app. Open source, Windows x64.

Build mcp server for any database based on GraphJin. It provides user-friendly UIs for setup multiple DB connection, flexible permission controls for user and table level,Customized for Ontology, MCP Client Test, Schema Browser, Running State monitor...,etc.

ViewGraph is a developer super assistant that captures live web pages as structured, agent-ready UI context, combining layout, DOM-like structure, selectors, styles, spatial relationships, screenshots, and metadata to help coding agents generate tests, audit interfaces, compare changes, and build faster.

Computer use for Grok Build: a plugin and MCP server that let the agent see the screen, click and type in desktop apps and browsers on macOS, Windows and Linux. Accessibility-tree first, with safety hooks. Built for UI testing in the dev loop.

MCP server for desktop UI automation — screenshots, windows, mouse, keyboard, UI Automation, OCR

CUIT — the deterministic feedback edge for agentic UI engineering. Recorder + harness + spec-gen + data warehouse. complex-ui-tester is the canonical npm/repo name.

Model Context Protocol server providing AI assistants with access to Flowbite UI components and an intelligent theme generator for Tailwind CSS

MCP server for React Native and Expo development

Precise verification for coding agents on Android: compact screens, impact analysis, verdicts with evidence, UI, performance and compatibility checks. CLI and MCP server.

Eyes and hands for AI agents on mobile devices. MCP server for Android & iOS.

Small Test Set for MCP-App SEP-1865

Your agent said done. It never watched it run. caught-in-4k turns UI recordings into frames an agent can see: what changed, what flickered, what never moved. CLI, MCP server and agent skill.

A virtual Wayland compositor an agent can use to test your desktop apps via MCP.

MCP server that gives AI coding agents visual diff capabilities for UI work

MCP server for native app testing — screenshot, OCR, click, type, find_text, template matching. macOS, Windows & Android.

AI-native cross-platform mobile automation (iOS Simulator + Android emulator), maestro yaml dialect superset

Visual frontend inspector via MCP. Screenshot, accessibility scan, device simulation, and audit — all from your AI editor.

Give your AI agents full control over any Electron app. Zero changes to your existing code. Made for AgentsRoom.dev.

Fresh, throwaway Windows machines for testing your apps: an MCP server and CLI that automate Windows Sandbox

Enterprise-grade Windows automation MCP server for AI agents — 53 tools including click_text, wait_for_text, structured OCR, UI Automation, and batch operations

Flipper alternative for Android — inspect any app via adb (mirroring, view hierarchy, screen flow, network), with an MCP server for Claude Code agents

TinkyVision + IsolatedTester by Luke Kist / TinkyBink: screen images, OCR/ASCII for text-only models, accessibility, and isolated macOS app testing over MCP.

MCP server that sees your UI like an user and measures it like DevTools. Cross-checks rendered pixels with DOM/CSS to catch visual bugs (clipped text, overlaps, font fallbacks, real contrast), extract design tokens and run UX/UI audits (WCAG, heuristics). Built on Playwright.

QualityPilot: 基于 MCP + RAG 的智能测试自动化平台 — 测试用例生成、API/UI 自动执行、失败分析、Bug 报告

One MCP server, 51 tools for AI agents on mobile + canvas UIs: iOS & Android automation, Maestro E2E, evidenced assertions, React Native/Metro debugging — plus a no-vision canvas/WebGL brain (Pixi/Konva/Fabric/Phaser/Three/Babylon) that drives game UIs like DOM elements, ~5x cheaper than screenshot loops.

Android emulator control for AI agents: an MCP server with 42 tools (env lifecycle, AVD/SDK management, UI automation with multitouch, adb shell, emu console, diagnostics) plus a self-hosted bridge with live H.264/Opus streaming and a token-protected browser viewer.

See and drive a GPUI app from the command line or MCP: snapshots with refs, clicks, typing, waits, screenshots and recordings

A generic, decoupled Windows UI Automation framework using gRPC.

8-phase evidence pipeline for Playwright, pytest, Jest, Cypress, Newman, k6, and JUnit failures. Scans git history, application logs, and config to produce confidence-scored root-cause hypotheses. Exposes as MCP server, CLI, and streaming web UI.

AI-driven cross-platform UI automation engine for Android, iOS, and Web. Your Agent inspects, decides, and acts — ScreenForge executes and generates pytest scripts with self-healing.

Go CLI and MCP server for managing Parallels Desktop VMs on macOS and inspecting, controlling, and screenshot-testing Windows applications.

Windows Computer Use for AI Agents. Both a tool (22 MCP tools for click, type, screenshot, OCR, UI inspection) and an agent (autonomous mission engine, macro recorder, intent-based discovery, event watchers). Built with opencode (DeepSeek V4). Ships as MCP server, web UI, and Tauri desktop app.

Zero-config visual testing for AI agents. Render project components with full Vite dependency resolution — no stories, no config.

MCP server for visual Android device control via ADB — screenshots, taps, UI inspection for Cursor and AI agents