Testing & QA MCP servers

Physical USB HID keyboard and mouse control via a Raspberry Pi Pico 2: move, click, drag, type, key combos and scroll, with a mock mode for testing.

Guarded AI mobile Appium testing, security scanning, verification, and fix-retest MCP tools.

Simulated smart home and lifestyle devices for testing an agent's reasoning and discovery capabilities.

API testing: per-project environments with variable interpolation, saved collections, multi-step flows, assertions, load testing and OpenAPI mock generation.

Website testing with Playwright: assertions, auto form-fill, persistent logins, network mocking, and accessibility, SEO, GEO and Lighthouse audits.

Frontend expert for Claude Code. Screenshots, Lighthouse, axe-core, code analysis, auto-fix.

Word .docx editing: live editing of open documents, tables, citations, footnotes, tracked changes, mail merge, redaction, accessibility audits and Zotero.

Validate HTML and CSS, audit technical SEO and accessibility, check JSON-LD and public links, and capture responsive screenshots.

Headless DHI MIKE+ urban-water modelling: model inspection, parameter editing, simulation runs with QA status, .res1d results reading and plotting.

MailSandbox (a fork of Mailpit) is a fast, zero-dependency email testing tool & API with a web UI, SMTP server, Postmark API emulation, and MCP server for AI-assisted debugging.

Local retrieval over ISTQB, OWASP, IEEE, ISO and EU AI Act QA standards, plus QA effort estimation, QA document review and JUnit/CSV flakiness analysis.

Live+headless Aseprite MCP: Unity export, art-QA, tilemaps, in-editor dialogs, update-aware

Open-source AI agent toolkit for building, inspecting, testing, and automating Roblox games in Studio.

JSON-driven E2E test runner with parallel Chrome pool execution and 16 MCP tools.

Accessibility MCP server and Agent Skills for AI agents. Requires Superpowers.

Code-aware browser testing that reads routes, forms and existing tests, runs Playwright scenarios, and keeps regression history and screenshot reports.

Undetected Chrome automation via nodriver for anti-bot protected sites: accessibility snapshots, input automation, network inspection and persistent sessions.

A MCP server that provides comprehensive website snapshot capabilities using Playwright. This server enables LLMs to capture and analyze web pages through structured accessibility snapshots, network monitoring, and console message collection.

Mobile E2E testing on macOS: iOS Simulator control, native UI automation, Maestro flows, React Native debugging and WebView DOM inspection.

Website audits: SEO, security headers and SSL, Lighthouse performance, broken links, WCAG accessibility, Schema.org validation, competitor gaps and robots.txt.

Utility tools with x402 micropayments: JSON validation, base64, hashing, UUIDs, regex testing, Markdown and datetime conversion, cron parsing and JWT decoding.

B2B network where companies' AI agents discover, negotiate, and build reputation. E2E-encrypted.

One-entry orchestrator for coding agents: jailed vault, FTS knowledge graph, 18-axis review, in-harness Chrome QA. Curated packs — not a 90k-skill dump

API testing tool with YAML tests and structured JSON failures agents can act on: run, validate, inspect, rerun failed tests and get fix plans.

In-page debug bridge for web apps: read the DOM, console logs and network requests and interact with the page, in any browser or Cypress/Playwright run.

Autonomous web app testing: run test cases in real browsers with pass/fail results and screenshots, and generate user stories, test cases and Playwright code.

Turn Lighthouse audits into coding-agent fix packs for Claude Code, Cursor, and Copilot.

Delivery-readiness QA and full official + Tapir API access for a running Archicad 29.

Spanish dialect localization: translate and QA-check text across 25 regional variants with register control, structure preservation and quality gates.

Ensemble testing of web pages for accessibility, usability, and standards conformity

Run AI market research: synthetic customer panels for concept testing, message testing, segments.

Self-hosted natural-language-to-SQL engine with validation for PostgreSQL, MySQL, Snowflake, BigQuery and DuckDB, plus document QA and semantic caching.

QA + a11y scanner: walks your running app's real user flows and reports what's broken.

MCP server for website health analysis — SEO, performance, accessibility, and security checks for any URL | 网站健康分析MCP服务器

Web accessibility scanning (WCAG 2.2 AA + KWCAG 2.2) with Korean remediation guides

Local-first document accessibility remediation using the canonical AlloFlow app pipeline.

A chaos-engineering and resilience-testing toolkit for Model Context Protocol servers.

NowSecure Platform mobile security testing: list applications, pull remediation findings and generate PDF reports locally.

Local QA MCP: scan URLs, inspect pages, generate Playwright repros, and run tests.

Journal entry testing (JET) for accounting audits. 15 screening rules, zero dependencies.

Python intent tracing MCP: map specs to pytest tests, monitor implementation progress, offline-only.

Enterprise-grade MCP server providing comprehensive testing capabilities for AI agents. Features 25+ testing tools including test execution, coverage analysis, test generation, debugging integration, mutation testing, flaky test detection, and visual regr

Reusable MCP server for WeChat DevTools mini program automation and testing.

See and drive any Windows app via the accessibility tree - no screenshots - plus 200+ native tools

MCP compliance testing: spec suites for MCP 2025-11-25 (88 tests) and 2026-07-28 (103 tests), auto-detected per server, for any MCP server over HTTP or stdio, with A-F grading, a CLI, an MCP server, and CI output.

Witness — the quality gate for agent-built web apps. Independent browser acceptance testing: CLI, MCP, AI-drafted checklists, visual regression, multi-browser. Agents self-test and pass; real browsers tell the truth.

Inbox placement testing across Gmail, Outlook, Yahoo, Mail.ru and Yandex: seed addresses, per-provider placement, SPF/DKIM/DMARC verdicts and screenshots.

Real-browser QA audits of a URL: broken signup, login and checkout flows, console errors, missing analytics, security headers, tap targets and accessibility.