Testing

SixSeven CLI + MCP server for AI-driven whitebox testcase generation

Agent-driven browser automation: a Chrome extension + Node bridge exposing composable browser_* tools for scanning, execution, and evidence capture.

MCP Workbench — test, inspect, and validate MCP servers

Is your AI agent capping? nocap runs the receipt and finds out if its 'done' claim is true — a lie detector for AI coding agents. Receipts over self-report.

AI 编程验证平台。让 AI 代码生成结果可验证、可信赖。MCP 协议原生支持，证据驱动。

Agent-first Chrome DevTools toolkit with a token-efficient CLI, 85 typed MCP tools, modal-free pipe transport, diagnostics, memory analysis, extensions, and WebMCP.

Give any AI agent a disposable email inbox in one tool call. MCP server for email verification, auth flows, and testing.

Generador automático de backends con Node.js, Express, Prisma y módulos configurables. Servidor MCP compatible con npx para agentes IA. Soporta PostgreSQL, MySQL, MongoDB y SQLite.

Record an AI agent once. Replay it without a model. Prove it told the truth. A tape format, a recording proxy, a deterministic player, and 37 checks for the ways agent loops lie.

An MCP server your coding agent uses to run, test, and diagnose the MCP server it is writing — spawn it, call its tools, restart it after an edit and see what changed, read how it died. Also a headless CLI with persistent sessions for agents that work fro

Argus — All-Seeing QA Guardian. An autonomous Claude Code agent that performs end-to-end quality assurance: codebase intelligence, Playwright exploration, ticket analysis, AC writing, tracker updates, and validation.

MCS (mcp-cs) — IEEE Computer Society Universal Campus Developer, Diagnostics & AlgoJudge Competitive Execution MCP Server

Next-generation multi-agent harness with 6 specialized agents, presets, security guardrails, and audit trail

Model Context Protocol server for Roverly — let a coding assistant read your app's map and run UI tests against it.

MCP server for browser inspection with Puppeteer - network monitoring and console error tracking

A local MCP server that breaks on demand. Test your client against auth failures, disappearing tools, flaky responses, and token expiry.

MCP Browser Server optimized for React Native Web with multi-tab support, screenshots, and persistent sessions

Pre-deploy checks for content sites: keywords, translations, links, claims, page SEO/GEO audit.

QA Automation Agent for Claude Code — multi-agent pipeline that analyzes repos, generates tests, validates, and creates PRs

Context-aware testing layer for Playwright MCP — scans your codebase, generates precise test plans, and produces CTO-level reports. Works with Claude Code and Cursor.