jank.ai

AI Testing Agents That Find Bugs for AI Coding Agents

Generate, execute, and report on test cases using real browser automation and multi-provider AI analysis. Built as an MCP plugin for Claude Code.

21 Tools
7 Bug Categories
3 LLM Providers
4 Export Formats
START TESTING SEE FEATURES
👾 👾 👾 👾 👾 👾 👾

WHAT IT DOES

Everything you need for AI-driven web testing, built into your Claude workflow.

🧪

Smart Test Generation

AI analyzes page screenshots and DOM to generate comprehensive test suites with steps, validation conditions, and priority scoring — automatically.

▶️

Real Browser Playback

Tests run in actual Chromium via Puppeteer. Natural language steps are converted to browser actions — clicks, typing, scrolling — with retry logic.

🐛

Multi-Category Bug Detection

7 specialized AI testers analyze your page in parallel: general, UI/UX, security, privacy, accessibility, content, and mobile.

WCAG Accessibility Audit

Full accessibility audit against WCAG Level A, AA, or AAA. Detects missing alt text, contrast issues, ARIA problems, keyboard navigation gaps.

🔄

Change-Aware Testing

After code changes, the plugin generates targeted tests for your modifications — including regression tests and edge cases — then runs them automatically.

📊

HTML Reports

Every test run produces a detailed HTML report with AI reasoning, screenshots at each step, timing data, and pass/fail results with a dark-themed timeline UI.

🌐

Site Crawler

BFS-based crawler discovers pages across your site, generates tests for each, and deduplicates — giving you comprehensive coverage with one command.

📤

Professional Export

Export tests to TestRail CSV, Cucumber/Gherkin, Selenium Python scripts, or JSON. Ready for your existing CI/CD and test management workflows.

🎥

Browser Recording

Launch a visible browser, interact naturally, and capture every click, keystroke, and scroll as replayable test actions. Record once, replay everywhere.

✏️

Test CRUD via Chat

Add, edit, update, and delete test cases by chatting. No need to leave the conversation — just say "add a test for login".

🧑‍💻

Multi-Persona Tester Panel

7 specialized AI testers analyze your page independently — each giving their own verdict with confidence scores.

📈

Test History Tracking

Every test run is recorded per URL with pass/fail counts, timestamps, and report paths. See quality trends over time.

██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██

MULTI-PERSONA BUG DETECTION

7 specialized AI testers analyze every page independently — like having a full QA team in your chat.

🔍

General Tester

Functional bugs, broken flows, logic errors

🎨

UX Tester

Layout, alignment, responsiveness, usability

🔒

Security Tester

XSS, injection, exposed data, misconfigs

🛡️

Privacy Tester

Cookie consent, tracking, data exposure

Accessibility Tester

WCAG violations, ARIA, contrast, navigation

📝

Content Tester

Typos, broken links, missing content, SEO

📱

Mobile Tester

Touch targets, viewport, responsive issues

━━━ Testers.AI Bug Detection ━━━━━━━━━━━━━━━
🌐 https://example.com
🤖 openai | 7 specialized testers
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

 ── Tester Panel ──
  🔍 General:      ✓ PASS
  🎨 UX:           ✗ 2 ISSUES FOUND
    • Inconsistent button sizes [P2 / 85%]
    • Missing hover state [P3 / 78%]
  🔒 Security:     ✓ PASS
  🛡 Privacy:      ✗ 1 ISSUE FOUND
    • No cookie consent banner [P1 / 92%]
  ♿ Accessibility: ✗ 3 ISSUES FOUND
    • Missing alt text [P1 / 95%]
    • Low contrast ratio [P2 / 88%]
    • Inputs missing labels [P1 / 91%]
  📝 Content:      ✓ PASS
  📱 Mobile:       ✓ PASS

━━━ Total bugs: 6 | Categories: 7 ━━━━━━━━
$ 
👾 👾 👾 👾 👾 👾 👾

QUICK START

Get up and running in under 2 minutes.

1

Install Dependencies

Clone the repo and install packages.

cd mcp-server npm install npm run build
2

Add to Claude Desktop

Add to your Claude config:

{ "mcpServers": { "testing": { "command": "node", "args": ["/path/to/out/index.js"] } } }
3

Configure API Key

Tell Claude to configure the plugin:

Configure testing plugin to use OpenAI with API key sk-...
4

Run Your First Test

Just ask Claude to test a page:

Quick test google.com Detect bugs on https://example.com
██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██

SLASH COMMANDS

Quick shortcuts available in Claude Code and as MCP prompts in Claude Desktop.

/test
Run tests on a URL. Auto-generates test cases, executes them, and produces an HTML report.
/test google.com search for AI testing
/test-changes
Test recent code changes. Auto-reads git history, generates targeted tests, runs them.
/test-changes http://localhost:3000
/gen-tests
Generate change-aware tests from conversation context. Summarizes changes and validates.
/gen-tests http://localhost:5173
/detect-bugs
Run comprehensive bug detection across 7 categories with specialized AI testers.
/detect-bugs https://myapp.com
██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██

LLM PROVIDERS

Choose the AI provider that works best for your needs. Switch at any time.

OpenAI

gpt-5-mini-2025-08-07

Fast, cost-effective. Great for high-volume test generation and quick bug scans.

Anthropic

claude-haiku-4-5

Precise reasoning. Excellent for detailed verification and nuanced bug detection.

Google Gemini

gemini-3.1-flash-lite-preview

Strong multimodal vision. Good for visual regression and UI analysis.

👾 👾 👾 👾 👾 👾 👾

ARCHITECTURE

How the pieces fit together.

Claude Desktop / Claude Code | | MCP Protocol (stdio) v +---------------------------+ | Testing MCP Server | | | | +---------------------+ | +--------------+ | | 21 MCP Tools |--+---->| Puppeteer | | | quick_test | | | (Chromium) | | | generate_tests | | +--------------+ | | play_test | | | | detect_bugs | | +--------------+ | | test_changes |--+---->| LLM Provider | | | crawl_and_generate | | | OpenAI | | | export_tests | | | Anthropic | | | record_test | | | Gemini | | +---------------------+ | +--------------+ | | | +---------------------+ | +--------------+ | | Report Engine |--+---->| HTML Reports | | | AI reasoning log | | | Screenshots | | | Screenshot capture | | | Timeline UI | | +---------------------+ | +--------------+ | | | +---------------------+ | +--------------+ | | Test Store + CRUD |--+---->| Per-URL | | | add / update / | | | Persistence | | | get / list / delete | | | + History | | +---------------------+ | +--------------+ +---------------------------+
██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██

EXAMPLE WORKFLOWS

Common patterns for using the testing plugin.

CI/CD Validation

# After deploy, in Claude: "Quick test https://staging.myapp.com" # Or for specific flows: "Quick test staging.myapp.com -- complete checkout with test card"

Post-Commit Testing

# In Claude Code after coding: /test-changes http://localhost:3000 # Auto-reads git diff, # generates targeted tests, # runs them

Full Site Audit

# Crawl + generate for site: "Crawl and generate tests for https://myapp.com starting from homepage, max 20 pages"

Accessibility Compliance

# WCAG AAA audit: "Run accessibility audit on https://myapp.com at AAA level" # Returns WCAG violations

Export to TestRail

# Generate then export: "Generate tests for myapp.com then export them as TestRail CSV" # Also: cucumber, selenium

Security Scan

# Focused security scan: "Detect bugs on https://myapp.com focusing on security and privacy categories only"