Testing

Testorax MCP server — autonomous AI browser testing. Paste a URL, get a bug report. Works with Claude Code, Cursor, Windsurf, Cline, and any MCP-compatible agent.

MetaGO Agent Harness 交付质量保证系统 —— 把 AI 自律从软约束变成硬门的强制门控框架。七层验证架构（L1技术/L2链路/L3契约/L4渲染/L5交互/L6状态/L7防御）+ L8缺陷猎杀（12维度）+ 十问自检 + 反绕过识别。对应 AGENTS.md V36.9.6 第十一/十四/十五章。

ICIL — Intelligence Campus Interactive Library. 216 courses, 29 faculties, 10 MCP tools. P@3=72.8%, R@3=94.4%, MRR=0.922. CI All Green.

MCP server for browser automation with 52 tools using Playwright

MCP server for Agent Target: fresh, deterministic HTTP-reliability trials for AI agents, scored on server-observed behaviour.

MCP server that converts test failures into Jira-ready defect reports — inside any MCP Client, no LLM API key needed.

Model Context Protocol (MCP) server for reading IDE output, test results, and linter problems. Integrates with Cursor, VS Code, and other IDEs for AI-assisted development.

Gate AI-written tests: heal safe drift, refuse to hide real bugs, sign a verifiable receipt.

Ground-truth UI element locators for AI coding assistants, plus a Locator Risk Score that flags which locators are likely to break your tests. Local CLI + MCP server, no hosting required.

Add an in-app AI support agent to React Native apps that understands UI, navigates screens, fills forms, and escalates to humans.

Browser automation for AI agents - integrates agent-browser with claude-flow swarms

Connect your OpenClaw agent to PlayClaw — the professional testing playground

Zero-dependency browser automation CLI. Raw CDP, 70+ commands, friction ladder, 3-tier stealth, CAPTCHA + press-and-hold solvers, proxy pools, MCP server. No Puppeteer/Playwright/Selenium.

NIA AI Web Evaluation Agent MCP Server - Autonomous browser testing and debugging

A powerful Claude Code skill for AI-driven web testing using Puppeteer MCP with auto-install and test reporting

Synthetic data generation Model Context Protocol (MCP) server. Generate realistic mock data for testing and development.

Complete API testing platform MCP server with 14 tools: performance testing (benchmark, load, stress, spike, soak, smoke, A/B compare, profile), functional validation, multi-step workflow chains, OpenAPI contract checking, fuzzing, security scanning, and

Testing library for MCP servers — in-memory test client, Vitest/Jest matchers, and test doubles for sampling and elicitation.

Browser automation for AI agents - integrates agent-browser with claude-flow swarms

Extract a visual contract from a reference page and measure an implementation against it