aiTest MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@aiTest MCP Server Test the login flow on https://example.com/login"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
aiTest MCP Server
AI-native browser testing, directly from your coding agent.
aiTest MCP Server connects AI coding tools (Cursor, Claude Desktop, Copilot) to the aiTest cloud testing platform. Describe what you want to test in plain English, and the AI engine handles the rest — planning, browser execution, root-cause analysis, and UX insights.
Quick Start
npx @aitest/mcpPrerequisites
Node.js >= 18
An aiTest API key (get one here) or run against a local dev server
One of: Cursor, Claude Desktop, or any MCP-compatible client
Related MCP server: Assert
Configuration
Set these environment variables (or use your MCP client's config):
Variable | Required | Default | Description |
| ✅ | — | Your aiTest API key ( |
| — |
| aiTest REST API base URL |
Cursor Setup
Add to .cursor/mcp.json:
{
"mcpServers": {
"aitest": {
"command": "npx",
"args": ["@aitest/mcp"],
"env": {
"AITEST_API_KEY": "aitest_sk_your_key_here"
}
}
}
}Claude Desktop Setup
Add to claude_desktop_config.json:
{
"mcpServers": {
"aitest": {
"command": "npx",
"args": ["@aitest/mcp"],
"env": {
"AITEST_API_KEY": "aitest_sk_your_key_here"
}
}
}
}Tools
aitest_run
Submit a new browser test job.
Parameters:
url — Target URL to test
description — What to test (natural language)
credentials? — Login credentials { email, password }
options? — Test config { max_retries, screenshot_mode, timeout_seconds }
Returns: job_id + estimated completion timeExample: "Test that the login page accepts valid credentials, rejects invalid ones, and shows appropriate error messages."
aitest_status
Check the current status of a test job.
Parameters:
job_id — The job ID from aitest_run
Returns: status (created/queued/executing/completed/failed) + timingaitest_report
Get the full test report (only available when job is completed).
Parameters:
job_id — The job ID from aitest_run
Returns: Summary, step-by-step results, root-cause analysis, UX insightsDevelopment
# Clone
git clone git@github.com:rongxianzhuo/aitest-mcp.git
cd aitest-mcp
# Install
npm install
# Build
npm run build
# Run locally (against local aiTest API)
AITEST_API_URL=http://localhost:8000/api/v1 \
AITEST_API_KEY=aitest_sk_test \
node dist/index.jsArchitecture
AI Coding Agent (Cursor / Claude)
│
│ MCP Protocol (stdio)
▼
aitest-mcp (thin proxy)
│
│ REST HTTPS
▼
aiTest Cloud Platform
│
├── FastAPI Server (Railway)
├── AI Engine (test planning + agent loop + analysis)
├── Supabase (auth + db + storage)
└── Browser Sandbox (Playwright / Browserbase)The MCP server is intentionally thin — zero AI logic, zero browser automation. It translates MCP tool calls into REST API requests and formats the responses for LLM consumption.
License
MIT — see LICENSE
Available Tools
3 toolsaitest_reportA
Get the complete test report for a finished job. Includes step-by-step results, pass/fail summary, root-cause analysis of failures, and UX improvement insights.
Inputs: job_id (required).
aitest_runA
Submit a browser test job to aiTest. Provide a URL and a natural-language description of what to test. The AI engine will plan, execute, and analyze the test, then return a report. Example: 'Test that the login form accepts valid credentials and shows the dashboard.'
Inputs: url (required), description (required), options, credentials.
aitest_statusA
Check the status of a previously submitted test job. Returns the current status (created, queued, executing, completed, failed) and timing info.
Inputs: job_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a distinct purpose: run submits tests, status checks progress, report retrieves results. No overlap or ambiguity.
All tools follow the consistent pattern 'aitest_<verb>', with clear imperative verbs (run, status, report).
Three tools cover the essential workflow (submit, monitor, retrieve results) with no redundancy. Slightly minimal but appropriate for the focused scope.
Covers the full lifecycle of testing: submission, status polling, and report retrieval. Missing operations like cancellation or listing are minor gaps.
Related MCP Connectors
Browser-based QA for AI-built software. Test pages with real browsers via agents.
Write, run and check natural-language browser tests of your web app from your AI assistant.
AI agents use your app like your users, in real browsers, and report what is broken or confusing.
Website checker for AI coding agents. Measures your site in a real browser, with evidence.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceBrowser-based QA testing for AI-built software. Agents open real browsers (via Selenium), navigate pages, fill forms, click buttons, and report findings. Two modes: targeted tests (30-90s) and full-site discovery scans (3-15min).-
- AlicenseAqualityDmaintenanceRun real Playwright E2E tests from your AI coding agent.48 npmMIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to automate and debug real Chromium browsers with capabilities like screenshots, video recording, performance analysis, visual regression testing, and OCR text extraction.13-
- AlicenseAqualityDmaintenanceEnables AI agents to perform comprehensive web application testing including visual, functional, performance, accessibility, and SEO analysis using browser automation without requiring API keys.7MIT