I want to test my web app in a real browser
Servers that run Playwright, Puppeteer, or Chrome DevTools. Your agent navigates your web app, reads console output, and flags failures.
MCP servers for this
- MCP server
- Official
browser-use
Browser Use
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
119kActive- Runs locally
- Remote
- API key
Setup documented for Claude Code, Cursor- MCP server
AIHawk
AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.
32kActive- Runs locally
- API key
- MCP server
Skyvern
Skyvern
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
23kActive- Remote
- API key
Setup documented for VS Code (GitHub Copilot)- MCP server
- Official
Keploy
Keploy
End-to-end API testing — generate and run tests from OpenAPI, curl, Postman, or real user traffic.
19kActive- Remote
- API key
- MCP server
SeleniumBase MCP
Stealthy browser automation, testing, and web-scraping via CDP Mode.
13kActive- Runs locally
- No auth
- Free
Setup documented for VS Code (GitHub Copilot)- MCP server
- Official
mobile-mcp
Mobile Next
MCP server for iOS and Android Mobile Development, Automation and Testing
10kActive- Runs locally
- No auth
Setup documented for Claude Code, VS Code (GitHub Copilot), GitHub Copilot CLI, Codex and 5 more- MCP server
- Official
agent-device
CallStack
MCP server for mobile app automation: verify, control, and debug iOS, Android, TV, and desktop apps
5.2kActive- Runs locally
- No auth
- Free
Setup documented for Claude Code, Codex, Cursor, Windsurf and 2 more- MCP server
jshookmcp
Search-first MCP server for JavaScript reverse engineering: 735 tools across 36 domains.
2.1kActive- Runs locally
- No auth
Setup documented for Cursor, Claude Desktop- MCP server
Chrome DevTools MCP
Google
MCP server for Chrome DevTools
54kActive- Runs locally
- No auth
Setup documented for Claude Code, VS Code (GitHub Copilot), Cursor, Claude Desktop and 1 more- MCP server
mcp-server-browser
MCP server for browser use access
39kActive- Runs locally
- No auth
Setup documented for VS Code (GitHub Copilot), Cursor, Claude Desktop, Windsurf- MCP server
- Featured
Playwright MCP server
Playwright
Playwright Tools for MCP
39kActive- Runs locally
- No auth
Setup documented for Claude Code, VS Code (GitHub Copilot), GitHub Copilot CLI, Codex and 7 more- MCP server
- Official
Argent
Software Mansion
Drive iOS Simulators, Android emulators, TVs and Electron/web apps from your coding agent
3.1kActive- Runs locally
- No auth
- MCP server
e2e
Open live web and mobile app sessions from an e2e project to inspect the app and try locators.
12kActive- Runs locally
- MCP server
- Official
Actionbook
Actionbook
Let your AI agent operate any website through a real, logged-in browser session.
1.6kActive- Remote
Setup documented for ChatGPT- MCP server
WebPerf Snippets
WebPerf Snippets
Measure Core Web Vitals and debug web performance with 56 snippets in a headless Chromium
1.5kActive- Runs locally
- API key
Setup documented for Claude Code- MCP server
Ui.Vision MCP
Ui.Vision
MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input
2.1kActive- Runs locally
- No auth
Setup documented for Claude Code, VS Code (GitHub Copilot), Cursor, Claude Desktop and 1 more- MCP server
testkube-mcp
Testkube
MCP server for Testkube - Manage test workflows, executions, and artifacts via AI assistants
1.7kActive- Runs locally
- Remote
- API key
- MCP server
- Official
Reticle
Reticle
Verify a running web app from the inside over MCP: look, act, observe, assert. No screenshots.
1.3kActive- Runs locally
- No auth
Setup documented for Claude Code- MCP server
invisible_playwright_mcp
AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.
887Active- Runs locally
Setup documented for Claude Code, Gemini CLI- MCP server
Unbrowse
Websites as APIs: read pages, run site tasks via learned APIs, cloud browser with saved logins.
810Active- Runs locally
- Remote
- API key
Setup documented for Claude Code- MCP server
browser
Lightpanda
Requesting 933 real web pages over the network on a AWS EC2 m5.large instance. See benchmark details.
37kActive- Runs locally
- No auth
- MCP server
Postman MCP Server
Give your AI agents trusted access to the full Postman platform.
325Active- Runs locally
- Remote
- API key
- MCP server
shaft-mcp
SHAFT browser automation, capture, and offline deterministic failure diagnosis
416Active- Runs locally
- MCP server
Flyto Core
Execution engine for AI agents. 412 modules: browser, file, Docker, data, crypto.
484Active- Runs locally
Skills for this
- Skill
- Official
test-scenarios
Pawel Huryn
Create comprehensive test scenarios from user stories with test objectives, starting conditions, user roles, step-by-step actions, and expected outcomes. Use when writing QA test cases, creating test plans, defining acceptance tests, or preparing for feature validation.
27kActive- No scripts
- Works offline
- Skill
- Official
- Featured
webapp-testing
Anthropic
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
184kActive- Plugin
- Works offline
- Skill
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
78kActive- Bundles scripts
- Works offline
- Skill
playwright-skill
General-purpose Playwright automation for coding agents
3.2kActive- No scripts
- Needs network
Setup documented for Claude Code, VS Code (GitHub Copilot), GitHub Copilot CLI, Codex and 3 more- Skill
browser-act
BrowserAct
Browser automation CLI for AI agents. NEVER run browser-act commands directly via Bash — always invoke this skill first. Use browser-act when a user mentions it by name, includes or asks to run a browser-act CLI command (e.g., browser-act browser list), or to: fetch, view, or extract rendered…
6.3kActive- No scripts
- Needs network
Setup documented for Claude Code, Codex, Cursor, Windsurf- Skill
- Official
appium-skill
TestMu AI
Generates production-grade Appium mobile automation scripts for Android and iOS in Java, Python, or JavaScript. Supports real device and emulator testing locally and on TestMu AI cloud with 100+ real devices. Use when the user asks to automate mobile apps, test on Android/iOS, write Appium tests…
381Active- No scripts
- Skill
- Official
behat-skill
TestMu AI
Generates Behat BDD tests for PHP with Gherkin feature files and MinkContext for browser testing. Use when user mentions "Behat", "PHP BDD", "Mink", "behat.yml". Triggers on: "Behat", "PHP BDD", "Mink", "behat.yml", "FeatureContext PHP".
381Active- No scripts
- Skill
unbrowse (skill)
Search and call websites through Unbrowse's hosted API or remote MCP, reuse indexed site tools, read pages, and learn missing routes in its cloud browser. Use for structured website tasks, and authenticated site access with Unbrowse.
810Active- No scripts
Setup documented for Claude Code- Skill
- Official
cypress-author
Cypress
Creates, updates, and fixes Cypress tests (E2E/end-to-end and component tests). Use when the user asks to create tests, add tests, write tests, update tests, test this file/component, new spec, or fix a failing or flaky test. Apply even when the user does not say 'Cypress' (e.g. 'create tests for…
47Active- No scripts
- Skill
- Official
cypress-explain
Cypress
Explains Cypress tests (E2E and component tests), and answers questions about Cypress use and behavior. Use when the user asks to explain how a test works, explain how Cypress works, review or critique a test without writing code. Apply even when the user does not say 'Cypress' (e.g. 'explain this…
47Active- No scripts