Testing

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

Code-aware browser testing agent — reads your codebase, understands functionality, tests every element, reports with screenshots. Works as MCP server for Cursor/Claude Code or standalone CLI.

Offline methodology engine and payload workshop for authorized penetration testing, CTF, security research, and education via MCP. STDIO or Streamable HTTP.

Your AI can already see the screen — it just can't measure it. uisight is an MCP server for web/responsive UIs: live mobile+desktop sessions, a measurement engine (contrast, touch targets, theme drift) that reports findings as text, and a panel you and yo

Read the public Sup wire over hosted MCP, or use local clients to claim, send, and verify receipts.

Conformance and robustness test suite for Model Context Protocol (MCP) servers. Runs in CI, zero dependencies. Catches stdout pollution, broken tool schemas, and bad JSON-RPC error handling before your agent does.

The most complete MCP server for API testing. 36 tools: HTTP requests (with token-optimized responses), assertions, request flows, OpenAPI import, mock data, load testing, collections, environments, native export/import, Postman import/export, cURL export

MCP server for pixel-level image comparison using pixelmatch

MCP server that gives AI agents eyes on your terminal — PNG screenshots, visual diffs, GIF recording, and full keyboard/text interaction

Run accessibility, contrast, and design token audits and file QA issues from your AI coding tool.

Free developer subdomains, DNS, disposable email, webhook capture, and MCP tools for Claude and Cursor

Suitest MCP server for IDE agents (Claude Code, Cursor, Codex) — generate, run, and publish QA tests from your editor. Includes blackbox DOM testing for any web app: no repo access required, just a URL and test credentials.

MCP server validation CLI — fast pre-publish diagnostic for Model Context Protocol servers. Schema validation, tool/resource/prompt health checks, scorecard reporting, CI-ready exit codes.

WolfeJam Technical Testing Certification - Score your MCP server for free. 52 tests, 9 tiers (49 scored + Tier 9 Receipt validation), from the creator of IANA-registered .faf format. Full leaderboard coming soon - what will your server score?

Live, end-to-end encrypted, ephemeral file transfer between your AI agent and any device.

MCP server for Human For AI — hire a real human operator for tasks that need physical presence, human perception, or human judgment: real-world verification, product testing, AI output review, data collection, and local errands. Free during the pilot.

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).

Colter Recommendation Audit CLI for Shopify product pages, evidence gaps, and agent-commerce monitoring. Includes Check, Fix, Test, Lens, UCP, ACP, MCP, and WebMCP.

MCP server providing screenshot capture capabilities for AI agents with multi-format support, PII masking, and security controls

MCP server for automating native Windows desktop apps — Playwright for Windows. Gives AI assistants (Copilot, Claude, Cursor) full control over WinUI3, WPF, WinForms, and Win32 apps with 55 UI automation tools. Built entirely with GitHub Copilot.