MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
qa-lab-agent-mcpgithub.com/Wesley-Gomes93/qa-lab-agent-mcpupdated this year
MCP-powered AI agent for QA — test generation, failure analysis, automation copilot
-
MCP server for browser automation and QA testing
npm MIT -
sentinel-qagithub.com/ahn283/sentinel-qaupdated this year
MCP server for AI-powered QA automation infrastructure
npm MIT -
@spike-land-ai/qa-studioupdated this year
QA Studio browser automation MCP server for spike.land
npm MIT -
MCP server for QA automation: 10 tools, 4 resources, 3 prompts for insurance testing. Full Claude Code ecosystem.
MIT -
qa-ai-mcp-server-gitsgithub.com/gits5213/qa-ai-mcp-server-gitsupdated this year
MCP server for QA automation: test scenarios, Playwright codegen, execution, and GitHub bug creation
npm MIT -
Flight booking Flask microservices with automated API tests (incl. RAG-generated cases), an MCP server that acts as a QA copilot, and GitHub Actions CI.
NOASSERTION -
MCP Server Selenium Playwright QA automation scripts and examples
-
MCP server for AI-powered signage QA automation
MIT ★ 1 -
playwright-mcp-rashaideh93github.com/rashaideh93/ultimate-qa-mcp-server-ai-driven-automated-testingupdated this year
AI-powered automated QA testing with Playwright and Model Context Protocol
npm MIT -
winvision-mcpgithub.com/zaxbysauce/zaxbyuiaupdated this year
Windows 11 desktop automation and vision-LLM QA via MCP
pypi MIT -
qa-mcp-servergithub.com/DwonnG/qa-mcp-serverupdated this year
MCP Server for automating QA tasks. Integrates Jira, GitHub, Jenkins, AWS, and Webex for seamless QA workflows.
MIT ★ 1 -
@kaneshir/lisa-mcpgithub.com/kaneshir/dev-infraupdated this year
Lisa MCP server — precompiled binary for AI-driven browser automation and QA intelligence
npm MIT -
Native app QA automation for AI agents over MCP — drive and test macOS, Windows, and iOS apps in the background, without stealing your focus or cursor
Apache-2.0 ★ 2 -
Argusgithub.com/ironclawdevs27/Argusupdated this year
AI-powered QA harness for Claude Code — automated bug detection via Chrome Dev-Tools Protocol, no test scripts required.
npm MIT ★ 5 -
Multi-agent AI pipeline (AutoGen + MCP) that auto-generates QA test scenarios and automation-ready test cases into Excel.
-
QA automation plugin for coding agents: app memory that keeps learning, test-case catalogs, Playwright skills, MCP server. Claude Code, Codex, Copilot/VS Code, Cursor, Antigravity, Gemini CLI, OpenCode.
MIT -
ta-studio-mcpupdated this year
TA Studio MCP server for Claude Code — AI-powered QA automation
npm MIT -
gridproofupdated this year
Gridproof your UI — automated spacing & grid QA in the agent loop (MCP server).
npm MIT -
Best AI QA Evidence Recorder MCP Server for Automated Testing 2026
★ 68 -
ordel-cliupdated this year
Ordel free CLI — local QA-automation for individual devs. Drives the deterministic ordel-engine and exposes it to a BYO coding agent over MCP. No account, no DB, no Ordel LLM.
pypi Apache-2.0 -
mcp-appiumgithub.com/KrishnaHarivindh/mcp-appiumupdated this year
Model Context Protocol server for Appium-based mobile testing and AI-assisted QA automation
Apache-2.0 -
tada-mcpactive
An automated QA assistant for AI-written code. Connects your coding agent to Tada's tools over MCP: create a test, check it in a real browser, and get a verdict (Passed, Failed or Inconclusive) with what to do next.
npm -
Five GTM automation systems on one platform: autonomous SDR agent, signal engine, MCP command center, outbound QA, lookalike finder
MIT -
The QAEverest MCP server — an AI QA copilot for any MCP client. Generate test cases grounded in your codebase, build and run automation suites, test AI agents, and run security and performance checks from Claude Code, Cursor, VS Code, JetBrains or Claude
npm MIT -
pursrgithub.com/0xheycat/pursrupdated this year
Visual QA, browser automation, accessibility auditing, screenshot diffing, and MCP tooling for coding agents.
MIT ★ 2 -
Universal automation execution layer for AI agents. 10 engines, 73 tools: browser, API, shell, email, database, cron, vault, visual QA, parallel execution via MCP. (Companion repo — architecture and interface only. Source lives in the private engine.)
-
Python browser automation with Camoufox, session persistence and a 17-tool MCP server. CLI and Python API for authorized QA, accessibility and agent evaluation.
MIT ★ 3 -
Vibetest MCP - automated QA testing using Browser-Use agents
★ 837 -
Humanize browser automation for AI agents, QA tests, and demos. Playwright-first — record sessions to video or runnable tests, and drive it over MCP from your favorite AI.
npm MIT ★ 29 -
goodhabitz-evalab-mcpupdated this year
MCP servers split into 4 specialized services: Studio (content creation), Dev (prompt engineering), Test (QA automation), Admin (configuration)
npm ISC -
MCP_SERVER_WITH_PLAYWRIGHT_AND_CLAUDEgithub.com/nikhilfufu/MCP_SERVER_WITH_PLAYWRIGHT_AND_CLAUDEupdated this year
An MCP server built in C# that exposes QA automation tools (like browser login) to AI clients. It uses Playwright for browser automation and ExtentReports for HTML reporting with screenshots, allowing AI agent (Claude) to run and inspect real end-to-end tests.
-
playwright-ai-frameworkgithub.com/SayanCispl/playwright-ai-frameworkupdated this year
This project is a QA automation framework built with Python, Playwright, and Pytest, enhanced by Allure reporting and a mock MCP server that integrates GitHub Copilot as the AI agent.
★ 1 -
Vibe code fast. Ship like an engineer. AI engineering framework packaged as an MCP server that enforces TDD, security scanning, pentesting, secret management, QA audits, and deployment to a securely configured VPS — automated with up to 100× fewer exploration tokens.
MIT ★ 11 -
This project implements a lightweight MCP (Model Context Protocol) server for ReportPortal using FastAPI. It pulls test metadata from ReportPortal and exposes it through a clean API for use in LLM-based tools, dashboards, or QA automation systems.
-
The complete end-to-end frontend engineering and design orchestrator for AI agents and developers. 16 pillars, MCP server, 3D WebGL, typography, motion, and automated QA.
npm MIT ★ 2 -
Minimal ffmpeg editing bench over MCP, Apache 2.0: probe, trim, concat, transform, overlay, audio mix, JSON-timeline render, automated QA. No UI, no HTTP port, small enough to audit. Full editing room with UI: video-atelier-mcp.
Apache-2.0 -
Agent-first E2E testing CLI
npm MIT ★ 29 -
@fasttest-ai/qa-agentupdated this year
FastTest Agent — MCP server that turns your coding agent into a QA engineer. Test, explore, and break web apps using Playwright.
npm Apache-2.0 -
argus-qagithub.com/argus-qa/argusupdated this year
AI-powered QA orchestrator with structured memory and MCP server
pypi MIT -
AI 코딩 에이전트가 브라우저를 직접 조작해 QA하게 하는 도구
MIT -
db90-qa-servergithub.com/dualboot/db90-qa-serverupdated this year
DB90 QA Intelligence MCP Server — pluggable QA ecosystem for the full SDLC
npm ISC -
@muggleai/mcp-qa-gatewayupdated this year
MCP Gateway for Muggle Test QA APIs - exposes QA workflows as MCP tools
npm MIT -
MCP Server de QA automatizado para Claude Code — testing, review y reporting integrado
npm MIT -
Automatic QA for Freejira review tasks: GitHub PR evidence, project checks and local Ollama. Durable reports, macOS/Linux services, MCP integration.
MIT -
MCP server for Claude: from a Jira export to verified Gherkin tests (demo, fictional data)
MIT -
Agentic AI Web Testing Platform for Antigravity, Claude Code & Cursor powered by MCP & Playwright
MIT ★ 7 -
Read-only MCP server for AI-assisted root-cause analysis of TeamCity build failures
npm MPL-2.0 ★ 8 -
Repeatable browser checks for coding agents. JSON scenarios, local Playwright evidence, CLI + MCP.
Apache-2.0 ★ 1 -
MCP server giving AI agents allowlisted, audited Android QA tools over adb: UI dump, tap, logcat, screenshots
MIT -
MCP server that runs allowlisted commands in iTerm2 and captures window screenshots as proof of work for manual QA
-
MCP server that turns JUnit test reports into QA insights for Claude and Cursor: flaky tests, regressions, RCA clustering, dashboards.
MIT -
cursor-mcp-qa-agentgithub.com/Ardaka/cursor-mcp-qa-agentupdated this year
A local MCP server, Cursor Agent rules, and safe reusable QA workflows in TypeScript.
MIT -
AI 測試大師 — MCP server driving pytest / Jest / Cypress / Go / Maestro. Analyze, generate, run, advise. Web + Mobile (iOS/Android/BlueStacks).
pypi MIT ★ 38 -
Deterministic, zero-hallucination agentic QA engine. Equips AI agents with cognitive heuristics and boundary fuzzing to autonomously test Web, Mobile, Desktop, and APIs.
npm MIT ★ 1 -
MCP server + Claude Code plugin for Playwright QA: user stories to verified tests, structured test runs, and self-healing locators with confidence and reasons.
npm MIT -
ai-qa-agent-mcpgithub.com/sadi-qa/ai-qa-agent-mcpupdated this year
TypeScript MCP server that analyzes Playwright JSON and JUnit XML reports to generate QA metrics, failure insights, bug-report drafts, and release recommendations.
-
MCP server & Claude Code plugin for Selenium in Python and Java: verified locators, user story to tests, and self-healing locators with an audit trail
pypi MIT -
Common QA MCP — one product-neutral MCP that routes test-case lifecycle requests to Walnut or SimplifyQA for any AI client. Launch over stdio via npx; install the Walnut QA agent with `init-agents`.
npm MIT -
MCP server & CI tool for self-healing Appium locators in Android and iOS apps: heals on the screen each test failed on, Python & Java Page Objects, verified re-runs, accessibility checks
pypi MIT