Deterministic Python Model Context Protocol (MCP) server & autonomous agent skill for Test Access.

A library, CLI tool, and MCP server for automated and scripted accessibility testing using VoiceOver (macOS) and NVDA (Windows)

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.

Free MCP server and agent skill that runs, diagnoses and fixes failing Playwright tests (TypeScript and pytest), and proves each fix by re-running it. Flaky verdicts, finds the commit that broke a test, blocks fixes that check less, posts CI fixes as PR suggestions, accessibility and Web Vitals audits. MIT, no account.

Web-app QA, testing & analysis for AI agents — 74 Playwright tools: authenticated flows (2FA/SSO), 25-action E2E workflows, hard assertions, session reports, and accessibility / SEO / GEO / Core-Web-Vitals + Lighthouse audits across a page or a full crawled site. Battle-tested by an AI agent on real apps.

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

CARBON AI testing harness with Jay: risk-based software testing, exploratory and regression checks, accessibility, triage, and local evidence reports via MCP.

Local, MIT-licensed AI test harness with 10 MCP tools and 11 prompts for risk-based test planning, focused testing, accessibility checks, evidence capture, screenshot maps and interactive HTML quality reports. Runs over stdio in one explicitly selected project. Your coding agent supplies AI and browser execution; CARBON records observed evidence and generates reports. No hosted backend, model API key or telemetry required.

Comprehensive accessibility testing MCP server with axe-core integration, annotated screenshots, batch testing, and multiple report formats

MCP server for Kali toolkit (docker) - 121 tools for AI-assisted security testing give agents access to all it needs!

AI-powered Selenium MCP server for browser automation — 74 tools with accessibility tree discovery, test generation, self-healing, and Selenium Grid parallel execution for AI agents

Lighthouse for AI agents — test if APIs are properly agent-accessible

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

MCP server exposing the official ChatGPT Desktop app (Ubuntu/Linux) as 6 MCP tools via AT-SPI accessibility — idempotent, interference-safe, stress-tested.

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.

The accessibility layer for AI coding agents, WCAG 2.2: static and rendered audits (light AND dark), contrast over images, blindfold usability testing, PDF/DOCX screening, caption quality, prefers-reduced-motion audit, evidence packs a human can sign. Zero deps

A comprehensive Model Context Protocol (MCP) server that provides web performance auditing, accessibility testing, SEO analysis, security assessment, and Core Web Vitals monitoring using Google Lighthouse. Enables LLMs and AI agents to perform detailed we

Point an app at two logged-in users and it finds the broken access control (IDOR). Deterministic browser perception + cross-identity authz testing for AI agents — drives your real Chrome over MCP or runs headless. Open-core, local, no account.

Test an access-control matrix (role x endpoint) for IDOR/authz gaps

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 that gives AI assistants access to a Kali Linux Docker environment for security testing

A conversational MCP server that gives Claude direct access to your dbt project and DuckDB — query tables, run models, test data quality, and explore lineage, all in plain English.

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.

Read, write, analyze and test the VBA inside Excel, Word, PowerPoint and Access files, and edit the document around it. No Office installation needed.

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.

MCP server giving AI agents full access to Julia's runtime via a live Gate — code execution, introspection, debugging, testing, and semantic search

OpenEmbedded/Yocto layer for embedded lab automation with CI/CD runners, flashing tools, power control, hardware testing, remote access and Agentic AI automation.

MCP server and agent skill for SEO and AI search visibility: audit AI crawler access, generate llms.txt, and build GEO/AEO prompt tests.

- A Vibe Coded Project - Connect Claude Code to local LLMs through LM Studio APIs via MCP bridge. Multi-model support, hot reload, dynamic MCP discovery. Access filesystem, database, web, git, and more. Zero API costs, full privacy, test coverage. Inspired by infinitimeless/LMStudio-MCP.

Open-source MCP server giving Claude first-class access to YouTube video transcripts as callable tools. Captions-first via yt-dlp with Whisper fallback for videos without subtitles. 26 unit tests, pip-installable, works with Claude Desktop and Claude Code.

MCP server for Adobe Commerce / Magento 2 developer documentation. Gives AI assistants (Claude, Cursor, Cline, Windsurf) direct access to developer.adobe.com/commerce — PHP modules, GraphQL, REST API, PWA Studio, App Builder, extensibility, MFTF testing,

MCP server for the Electronic Code of Federal Regulations (eCFR). Read FAR, DFARS, and all agency FAR supplements with point-in-time version history. Provides FAR clause lookups, DFARS lookups, agency FAR supplement access, version history, and full-text CFR search across all 50 titles. Updated daily from the source of record. **13 tools.** No authentication required. Hardened across 6 audit rounds with 240 regression tests. Built for GS-1102 contracting officers and acquisition policy researchers.

cdpilot is a browser automation CLI and local MCP server that talks to Chrome, Chromium, Brave or Vivaldi directly over the Chrome DevTools Protocol, with no Puppeteer, Playwright or Selenium and no browser download. Its 45 MCP tools cover navigation, clicks and form filling (including inside cross-origin iframes), accessibility-tree snapshots, screenshots, test assertions, a page's own WebMCP tools, and Web Bot Auth request signing. `cdpilot connect` attaches to a browser you started yourself, so a person can clear a login or CAPTCHA and the agent continues; cdpilot never closes that browser. Every feature has a runnable example with its real output: https://github.com/mehmetnadir/cdpilot/tree/main/examples

**Run GPU workloads, deploy AI models, access inference APIs, and execute AI agents using Badgr's MCP server.** Badgr is an AI compute and workload execution platform for developers, coding agents, and AI assistants. Run workloads on cloud GPUs or compatible customer-owned GPUs (BYO GPU), with cost controls, execution logs, and verified results. **What can Badgr do?** - **GPU Compute / AI Workloads:** Run Python scripts, machine learning jobs, batch inference, and supported ComfyUI workflows. - **AI Model Deployment:** Deploy and serve LLMs using compatible runtimes such as vLLM and SGLang. Get a verified, OpenAI-compatible inference endpoint. - **AI API / LLM Inference:** Make AI API requests with response validation, supported fallback routing, and bounded execution. - **AI Agent Execution:** Launch coding and testing agents, run tasks, check acceptance criteria, and retrieve execution receipts. **Key features:** Cloud GPU execution, BYO GPU support, model serving, AI agent jobs, workload verification, execution logs, cost limits, and deployment management. Connect Badgr to your MCP-compatible AI assistant to execute real workloads instead of just generating instructions. Get started: https://aibadgr.com **Requires a Badgr API key. GPU workloads and other paid execution may incur usage charges.**

Autonomous QA scanner: point it at your running app and it walks the real user flows in a headless browser and reports what's actually broken: broken pages/links, console and network errors, empty/placeholder data, broken forms, state-loss, bad loading/er

Free, open-source desktop QA browser for testing your own website forms by US location (state, city, ZIP), emulated device and browser. Windows, Linux, macOS.

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

Mobster CLI and MCP server. Let Claude Code, Codex and Cursor drive a real iPhone or iOS simulator and check what's on screen.

MCP server for macOS desktop automation. Background GUI testing, 30 tools, audio capture, camera, virtual desktops. Built in Rust.

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

Cognitive browser automation that thinks like your users—and helps AI agents navigate too. Simulate real user cognition with abandonment detection, constitutional safety, chaos engineering, and UX friction discovery. Sites that pass CBrowser's cognitive t

MCP server, command line and TypeScript library that test, drive and measure iOS and Android apps on simulators, emulators and real phones.

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

Claude Code plugin for UXMachine: measure your site in a real browser and compare with the last measurement.

Argus — the QA layer for AI-assisted development. Claude-native (MCP) Chrome audits across 67 categories — errors, visual regressions, a11y, security, performance — no test files, secrets redacted by default (Aegis).

MCP server for Linux desktop GUI automation on KDE Plasma 6 Wayland — 29 tools for virtual and live sessions

Android emulator your AI agent drives on under half the RAM of Android Studio's (1.4 GB vs 3.5 GB): a text screen outline instead of screenshots, and per-device network, battery, location, screen, font and Android version. CLI + MCP server.

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

Accessibility and SEO panel for vite dev that gives the issues to your AI agent over MCP: WCAG, ARIA and SEO checks on the page, axe-core when installed, plus a Playwright helper and a CLI for CI

🔭 Your coding agent, turned into a QA tester for any web app. Finds what is broken and shows you the proof: pictures, replays, journey videos and test reports. Over MCP, with Claude Code, Cursor, VS Code, Codex, Gemini CLI and more.

Audit any URL against WCAG 2.2 from the terminal, in CI, and from AI agents over MCP.

Render testing built for AI agents: a map of the screen instead of screenshots, actions by intent, map-to-map comparison. MCP server and library. Verified by Healer.

Auditoría de accesibilidad agéntica: axe-core, zoom y espaciado WCAG, un agente de teclado que mide el foco y Gemini Vision. Web, GitHub Action, servidor MCP y CLI.

MCP server that lets an AI coding agent run and drive a real GPUI desktop app: screenshots, element tree, clicks, typing, scrolling, dialogs and file pickers, headless or in a sandboxed KDE Plasma session on Linux

MCP server for dynamic Playwright browser pool management — 75 tools, 28 built-in UI audits, 42 CLI commands, 143 device presets, golden profile auth. Built for Claude Code, Cursor, and AI-assisted web development.

LINC crucible — release mirror of LINC Innovations' device tooling (Apache-2.0)

Android automation from Python: test your apps on real phones, script the tasks you repeat and run many phones at once. No ADB, no USB cable, no root.

Deterministic, MCP-native delivery QA for AI-generated web pages

UXMachine MCP server: measure a website in a real browser and get observations with evidence.

MCP server for Storybook - provides AI assistants access to components, stories, properties and screenshots