AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Workflow Automation/
muggle-ai-works
muggle-ai-works logo

muggle-ai-works

Active·★ 16·MIT·Updated 2026-10-22

Run real-browser E2E acceptance tests on your web app from any AI coding agent. Generate test scripts from plain English, replay them on localhost, capture screenshots, and validate user flows like signup, checkout, and dashboards.

#E2E Testing#AI Agents#Browser Automation#Acceptance Testing#Development Workflow#Test Automation#MCP Tools
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides
$ Install
$ npm install -g @muggleai/works
↗ Visit site★ GitHub
01

Features

01AI drives a real browser against your localhost across desktop and mobile resolutions, clicks through flows like a user would, and reports failures with step-by-step screenshots.
02Handles the full development cycle: code the feature, run unit tests, run E2E acceptance tests, triage failures, and open a PR with evidence.
03Provides 70+ MCP tools for custom workflows, including project management, test case generation from plain English, script replay, and batch-run regressions.
02

Compatibility

Claude Code
Integration
Verified via docs
Cursor
Integration
Verified via docs
Codex
Integration
Verified via docs
Windsurf
Integration
Verified via docs
Node.js
Runtime
Verified via docs
03

Quick start

1
$ npm install -g @muggleai/works
04

Use cases

↳Test a feature on localhost: Describe what to test in English, and the AI will find or create test cases, launch a real browser, and report results with screenshots.
↳Autonomous dev pipeline: Complete the full development cycle from requirements to PR in one command, with AI handling coding, unit tests, E2E acceptance tests, and PR creation.
↳Direct MCP tool calls: Utilize any of the 70+ MCP tools directly from your AI assistant to build highly customized E2E acceptance workflows.
05

Alternatives

⚡Top VS:
VSopentakeoff★650→VSoreilly-ai-agents★322→VSiPolloWork★7.1k→

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
VS
ProxmoxMCP-Plus
★613
→
opentakeoff logo
opentakeoff★ 650
Open-source (Apache-2.0) PDF takeoff for construction & flooring — the first engine an AI agent drives natively over MCP, not bolted on. One-click room detection, materials + quantities, built for preconstruction. Runs entirely in your browser.
VSCompare→
oreilly-ai-agents logo
oreilly-ai-agents★ 322
An introduction to the world of AI Agents
VSCompare→
iPolloWork logo
iPolloWork★ 7.1k
iPolloWork — local-first AI agent workspace with Design and Video tools
VSCompare→
ProxmoxMCP-Plus logo
ProxmoxMCP-Plus★ 613
Use MCP and OpenAPI to safely control Proxmox VE VMs, LXCs, backups, and snapshots from LLMs and AI agents.
VSCompare→
iphone-use logo
iphone-use★ 333
响应快 省Token， Let AI agents (Claude Code, Codex, any MCP client) drive a real iPhone · 让 AI agent 操作真实 iPhone：读屏、点击、输入、滑动，USB 或 Wi-Fi，自有 XCTest runner，可回放的 App flow。Open source, self-hosted on macOS.
VSCompare→
growth-engineer logo
growth-engineer★ 244
Open-source catalog of go-to-market tools and workflows, written as markdown files any agent can run. Includes a read-only MCP server.
VSCompare→
cli logo
cli★ 48
Runtime intelligence system that makes MCP servers debuggable, testable, and safe to run in production.
VSCompare→
mcp-dev-latam logo
mcp-dev-latam★ 274
Open-source MCP servers for Latin American commerce — Pix, NF-e, banking, fiscal, logistics, and messaging across Brazil, Mexico, Argentina, Colombia, Chile, and Peru. MIT, on npm.
VSCompare→
See all alternatives →
multiplex-ai /
muggle-ai-works
↗

Your AI coding agent writes code fast — we make sure the web product actually works. Paste a URL, the agent clicks through signup/checkout/dashboards like a real user, reports failures with screenshots. Currently web only. Works with Claude Code, Cursor, Codex, Windsurf.

16MIT
Last commit1d ago
StatusActive
CategoryWorkflow Automation
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit