Testing

Scans live pages with the AudioEye rules engine and maps accessibility issues to JSX source.

Replayable browser automation: Jev picks the element, a gate blocks risky actions, every run traces.

Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.

Web-app QA for AI agents: 73 Playwright tools — auth, E2E, a11y/SEO/GEO, Web Vitals + Lighthouse

Model Context Protocol (MCP) server for Tern E2E testing platform

Run local prompt regression checks from prompt-response logs in AI coding assistants.

Local multi-channel message emulator for E2E testing, with MCP tools for LLM agents.

Windows desktop automation that re-reads only what changed: 7x fewer tokens per task.

List, create and move tasks through todo, in progress and done.

MCP server (streamable HTTP, no auth) at https://humanforai.dev/mcp where an AI agent hires a verified human operator: real-world verification, product testing, AI output review, data collection, and physical-world tasks.

An MCP server that created for demo

Visual accessibility inspector. WCAG contrast, touch targets, heading audits, screenshots.

Check generated audio, video and stills for defects. Returns a verdict, not more media.

Test generation, mocks, coverage analysis for AI agents

Polyglot MCP test generation with 8-section contract enforcement across Python, TS, Java, Go, C++.

KATATAN E2E testing agent set — Playwright + KATATAN MCP integration

Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.

Contract testing and quality gates for spreadsheets created by AI agents.

Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.

Read-only table diffs with segment attribution: which slice of your data changed.