- Conduid
- Marketplace
- #test-automation
MCP servers tagged test-automation
143 live MCP servers tagged "test-automation", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with test-automation.
Agentic Ui Testing
Write Automated UI tests as intent, not selectors. A four-step codelab where Antigravity CLI (Gemini) turns plain-English intent files into Playwright specs that survive a redesig…
Flowcheck
Repeatable browser checks for coding agents. JSON scenarios, local Playwright evidence, CLI + MCP.
Playwright Ui Automation Framework
This repository contains an web test automation framework developed and tested by using Playwright with TypeScript for implementing and executing automated tests.
Aat
Model your API as a graph once. Get long-chain integration tests, layer × environment matrices, CI-ready runs, and an MCP server for AI coding tools — all from the same YAML.
Deltawright
Action-scoped delta + actionability layer for Playwright agents: after one action, it reports what changed on the page and whether the agent can actually act on it — using Playwri…
Synthetic Test Fabric
Generic engine for autonomous synthetic test loops: simulation → browser flows → scoring → feedback
Copse
Drive & assert a running Cocos Creator game through its live node tree — no pixels, no input simulation. Runtime sibling to coir.
Qa Tools Demo
A practical demo repository showing how QA teams can use VS Code, AI assistants, and reusable tools to turn requirements into structured test scenarios and executable workflows. I…
Stockwatch Qa
Playwright + Python framework validating real-time stock data in a custom trading dashboard. UI automation via Playwright, API validation via finnhub-python, and AI-assisted test…
Kadeep CLI
KaDeep Studios CLI and releasegate: AI end-to-end testing from your terminal, CI/CD and coding agents (MCP). Run tests on web, mobile and desktop and get a go / no-go for every re…
AI Test Pilot
LLM-driven test generator: schema-validated scenarios → runnable pytest & Playwright tests, with typed-input construction, golden/characterization mode, failure triage, and an MCP…
Qualitest Intellij Plugin
质衡 Qualitest Helper — IntelliJ 插件：扫描 Spring Controller 并上传接口到质衡平台
Gettemp Email Testing
Open-source disposable inbox helpers for Playwright and automated email verification testing.
Jevitate
Autonomous browser testing that turns discovered bugs into deterministic regression tests. A model may choose what to try; only browser evidence decides pass or fail. CLI + MCP se…
Mobium
Mobile app automation for AI agents and humans: Android emulators and phones, iOS simulators and iPhones, and Fire TV, driven from one Go binary through a CLI, an MCP server and f…
Report Bridge
Import test results into a shared IR and preview Cucumber-style, Allure-like, and Extent-like reports.
AI Test Failure Analyzer
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-…
AI Agent
LLM-powered test automation framework: agent workflows, DOM reasoning, and schema-based test generation.
Lunarpass Playwright Tests
Testes E2E do LunarPass com Playwright + TypeScript, Page Objects, validação no banco e agentes de IA (Claude Code + Playwright MCP))
Honeyrail
Open-source runtime for long-horizon, verifiable engineering work.
Authstunt
The acquireAccount() the Playwright docs tell you to write yourself: self-hosted test identities with real mailboxes, where every claim binds exactly one message.
Custom MCP
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 direct…
Playwright MCP Server
A production-ready Java-based Model Context Protocol (MCP) server that bridges LLMs with a live Chromium browser using Playwright Java.
Tap
Host-driven end-to-end testing for Android, in Kotlin or Python: one server per machine, a separate on-device driver, JUnit 5 and pytest clients, and an MCP server for coding agen…
Two Go
Zero-dependency fluent API and service testing for Node.js: chainable HTTP, rich assertions, soft assertions, polling, snapshots, sessions, faker and a utility belt, plus an optio…
Flowproof
Agents are starting to run real business processes. flowproof tests them like anything else: record one real run, then replay it on every commit with zero LLM calls, asserting whi…
Zeno Mobile Runner
Deterministic mobile UI checks for AI coding agents. One Zig binary drives real iOS/Android devices, returns a typed pass/fail, and writes a replayable trace you can gate a merge…
Playwright Test Framework MCP Example
This repository provides an empty Playwright test framework that was designed to test AI and Playwright MCP (Model Context Protocol) in course
Selenium Selfhealing MCP
An MCP server that automatically fixes broken Selenium test locators when UI changes occur, reducing test maintenance overhead.
Quality Skills
107 production-grade QA engineering skills for AI agents — frontend, API, performance, mobile, security, CI, and AI/LLM testing. MCP-ready: works with Claude Code, Claude Desktop,…
Mockpost
Local emulator for E2E testing: fake SMTP, Telegram, WhatsApp, SMS, push, Slack, Discord, Stripe & OAuth with a web timeline and MCP server for LLM agents.
Taichi
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 a…
Github Action
Run Shiplight end-to-end tests in CI on every pull request
Local Testing Agent
Multi-language testing automation MCP server for Claude Code and AI assistants. Supports Python, JS/TS, Go, Rust, Java, and Ruby with automated test discovery and execution.
Simple Todo App
Simple test application used in course Playwright + AI + MCP
Nextcloud Sync Lab
MCP for Nextcloud server and desktop client synchronization scenarios
Playwright Flake Triage
Turn Playwright's "flaky" label into a ranked, root-caused triage report. Zero dependencies.
TestTrout
🐟 The testing assistant for coding agents. Reads your repo, connects to your deployment, ranks what's untested, writes real tests, runs them — driven over MCP.
Opentext Alm MCP
Connect AI agents to HP ALM via the Model Context Protocol (MCP)
Opencode Browser Automator
Autonomous Web Agent Toolkit 2026 - AI Browser Automation for Testing & Scraping
Frap
Deterministic UI engine for tests and agents — stable locators and self-healing without ML in core; optional LLM enhancements and MCP tools when you need them.
Rf Test Agents
Universal Robot Framework test agents — plan → generate → heal — driven on live applications through the rf-mcp (RobotMCP) MCP server. Technology-agnostic: web, HTTP APIs, mobile.
Robotframework Sapfx
SAP test automation for Robot Framework: one business vocabulary across three channels (SAP GUI desktop, Fiori/SAPUI5 web, OData and RFC API), with self-healing locators and AI ag…
Snapdrive Ios
AI agents drive iOS Simulator to generate snapshot baselines and run visual regression tests.
ITestAgent
Local TUI Agent for iPhone real-device and simulator testing: understand iOS projects, drive real devices, collect evidence, analyze failures, output reports.
Playwright Flow Tester
A powerful Flow Tester MCP for parameterized UI/UX testing with enhanced logging and MCP-native artifacts. Built with pure Playwright automation and zero external LLM dependencies.
Agentqx
Agentic E2E testing from any URL. Paste your app’s URL, walk away, come back to a Playwright suite that’s been run, fixed, and hardened.
Genxevo AI Automation Agent Python Selenium
An MCP server that lets AI coding agents diagnose and repair Python Selenium UI automation from real evidence — live DOM, real test results, verified fixes.
Testsprite
TestSprite — independent third-party profile of a public API surface, by API Evangelist. TestSprite is an AI-powered software testing platform (a Techstars-backed company) that gi…
Genxevo AI Automation Agent Csharp Selenium
An MCP server that lets AI coding agents diagnose and repair C# Selenium UI automation from real evidence — live DOM, real test results, verified fixes.