Do these 3 things before closing this tab:
1Clear out junk files and repair common Windows errors2Fix the driver behind crashes, sound loss and screen glitches3Repair Windows errors before they cause bigger problemsClaude Code can use a real browser through an MCP integration. Choose Playwright MCP for repeatable automation in an isolated browser, Chrome DevTools MCP to inspect and debug a live Chrome session, or Claude in Chrome to work through Anthropic’s extension alongside an existing Chrome workflow. Treat any signed-in browser as sensitive: the agent can inspect and interact with the page data it can access.
Choose the browser connection that matches the job
| What you need | Best fit | Why |
|---|---|---|
| Repeatable end-to-end tests or a clean browser context | Playwright MCP | It provides structured accessibility snapshots and browser automation and assertion tools. |
| Live-page debugging with console, network, DOM, performance traces, or Lighthouse | Chrome DevTools MCP | It is designed for live-browser inspection through Chrome DevTools Protocol. |
| Claude operating in an existing Chrome workflow | Claude in Chrome | Anthropic documents a direct Claude Code integration for build-test-verify work. |
| Reuse an already-running Chromium session from Playwright | Playwright MCP with a CDP or channel connection | Playwright documents connections to a Chrome or Edge channel and Chromium CDP endpoints. |
These are different access models, not interchangeable names for the same setup. An isolated automation context is usually the safer default for tests; a live or signed-in browser is useful when the state you need to inspect already exists there.
Set up Playwright MCP for isolated automation
Playwright MCP is Microsoft’s browser automation and end-to-end testing MCP server. Playwright’s official setup guide requires Node.js 20 or newer. Install it for Claude Code from a terminal:
claude mcp add playwright npx @playwright/mcp@latestThe command registers an MCP server named playwright and uses npx to run the current package. Package versions and setup commands can change; consult Playwright’s documentation if the command no longer works as written.
Quick wins for a faster PC:
Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Repair Windows errors before they cause bigger problemsFix Now →#1 Best Overall
- CRISP CLARITY: This 23.8″ Philips V line monitor delivers crisp Full HD 1920x1080 visuals. Enjoy movies, shows and videos with remarkable detail
- INCREDIBLE CONTRAST: The VA panel produces brighter whites and deeper blacks. You get true-to-life images and more gradients with 16.7 million colors
- THE PERFECT VIEW: The 178/178 degree extra wide viewing angle prevents the shifting of colors when viewed from an offset angle, so you always get consistent colors
- WORK SEAMLESSLY: This sleek monitor is virtually bezel-free on three sides, so the screen looks even bigger for the viewer. This minimalistic design also allows for seamless multi-monitor setups that enhance your workflow and boost productivity
- A BETTER READING EXPERIENCE: For busy office workers, EasyRead mode provides a more paper-like experience for when viewing lengthy documents
What it can do
Playwright MCP uses structured accessibility snapshots, rather than requiring a vision model to interpret every page. Its documented capabilities include navigation, clicking, typing, form filling, file uploads, dialog handling, screenshots, PDFs, console messages, network inspection, and test assertions. That makes it suitable for flows where Claude needs to find controls by their accessible information and repeat a sequence of actions.
Connect to an existing Chromium browser
If the task depends on a browser that is already running, Playwright documents channel and Chrome DevTools Protocol (CDP) connections. The --cdp-endpoint=chrome option can attach to a running Chrome or Edge channel; a Chromium CDP endpoint can also be supplied as a URL such as http://localhost:9222.
A CDP connection changes the risk profile: Claude is no longer working only in a fresh automation context. Use a dedicated browser profile and expose only the session needed for the task. Follow Playwright’s current instructions for the precise connection configuration, since the endpoint and browser launch setup must match your local environment.
Set up Chrome DevTools MCP for live debugging
Google’s Chrome DevTools for agents guide describes chrome-devtools-mcp as a way for coding agents, including Claude Code, to control and inspect a live Chrome browser. To install it through the Claude Code plugin interface, run these commands inside Claude Code:
Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchWindows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallRank #2
- CRISP CLARITY: This 22 inch class (21.5″ viewable) Philips V line monitor delivers crisp Full HD 1920x1080 visuals. Enjoy movies, shows and videos with remarkable detail
- 100HZ FAST REFRESH RATE: 100Hz brings your favorite movies and video games to life. Stream, binge, and play effortlessly
- SMOOTH ACTION WITH ADAPTIVE-SYNC: Adaptive-Sync technology ensures fluid action sequences and rapid response time. Every frame will be rendered smoothly with crystal clarity and without stutter
- INCREDIBLE CONTRAST: The VA panel produces brighter whites and deeper blacks. You get true-to-life images and more gradients with 16.7 million colors
- THE PERFECT VIEW: The 178/178 degree extra wide viewing angle prevents the shifting of colors when viewed from an offset angle, so you always get consistent colors
/plugin marketplace add ChromeDevTools/chrome-devtools-mcp
/plugin install chrome-devtools-mcp@chrome-devtools-pluginsThe equivalent MCP server configuration runs npx -y chrome-devtools-mcp@latest. Use the plugin flow or the MCP configuration appropriate to your Claude Code setup; avoid configuring both unless you specifically intend to run both integrations.
When this option is useful
The official Claude marketplace listing includes tools for clicking, typing, filling forms, uploads, dialogs, mobile emulation, screenshots, DOM snapshots, JavaScript execution, console messages, network requests, performance traces, memory snapshots, and Lighthouse audits. This makes Chrome DevTools MCP a good fit when a bug needs to be reproduced in the same live page whose console and network activity you are examining.
Google’s guidance warns that browser content is exposed to the agent: it may read, inspect, debug, and modify data in an active authenticated session. Use a separate Chrome profile or narrowly scoped test account for sensitive work. Do not connect a personal profile that contains unrelated credentials and private tabs.
Use Claude in Chrome for Anthropic’s signed-in workflow
Anthropic describes Claude in Chrome as a browser extension that can be launched from Claude Code. Its documented build-test-verify workflow is to build in Claude Code, deploy to a URL the browser can reach, test and verify in the browser, then debug with console logs, network requests, and DOM state. Anthropic highlights design verification, live debugging, and automated testing as uses.
Rank #3
- Clear visuals. Fluid motion: A 144Hz refresh rate and 1ms MPRT deliver smooth, tear‑free motion across work, gaming, and streaming for clearer, more fluid viewing.
- Eye comfort: TÜV Rheinland 3‑star* certification reduces harmful blue light while preserving stunning color quality without compromise. *TÜV Rheinland 3-star eye comfort certification.
- Wide viewing angle: Get consistent views across a wide 178° /178° viewing angle.
- In-Plane Switching (IPS): See excellent color accuracy and consistency across wide viewing angles with In-plane Switching (IPS) technology.
- Ultra-thin bezels: Maximize your viewing experience with thin bezels.
Anthropic Support says Claude in Chrome is available on paid Pro, Max, Team, and Enterprise plans, but rollout and administrator conditions vary by plan. The support page is dated August 26, 2026; verify the current availability and any organization controls in Anthropic’s support documentation before relying on it.
Anthropic’s wording is direct: “Claude in Chrome allows Claude to interact directly with websites on your behalf.” Accordingly, use this option only when that level of interaction is appropriate for the site, account, and organization policy.
Give Claude Code access step by step
- Decide which browser state is required. For repeatable tests, choose Playwright MCP and an isolated context. For live debugging, choose Chrome DevTools MCP. For an existing Chrome workflow through Anthropic, choose Claude in Chrome.
- Check prerequisites and current instructions. For Playwright’s documented install, confirm Node.js 20 or newer. For the other integrations, check the official setup page and whether your organization permits the required browser access.
- Register or install the integration. Run the Playwright command in a terminal, the Chrome DevTools plugin commands in Claude Code, or follow Anthropic’s current Claude in Chrome setup.
- Start with a low-risk page. Ask Claude to open a public or local test page and perform a harmless action, such as reading a heading or taking a screenshot. Confirm the connected browser and page are the ones you intended.
- Grant only the session needed. If a task requires authentication, use a dedicated profile or scoped test account. Do not assume the MCP connection limits what the agent can see once attached.
- Make the task verifiable. Ask for concrete checks—such as the resulting page title, a visible confirmation, or a relevant console/network finding—rather than relying on an unverified claim that an action succeeded.
Security and operational choices
For CI and regression testing
Prefer Playwright’s isolated context for automated tests. A clean context reduces accidental dependence on a developer’s cookies and makes the test conditions easier to reproduce. Keep credentials and test data limited to what the test needs.
For a local app bug
Chrome DevTools MCP is useful when the page is already open and you need Claude to connect a visible symptom with console errors, network requests, DOM state, or performance evidence. Review any proposed JavaScript execution or page changes before allowing them to affect a production account or site.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
Rank #4
- CURVED FOR ENHANCED ENGAGEMENT: An immersive viewing experience with a curved monitor that wraps more closely around your field of vision; It creates a wider view, enhancing depth perception and minimizing peripheral distraction
- SMOOTH PERFORMANCE FOR SEAMLESS CONTENT: Stay in the action when playing games, watching videos, or working on creative projects; The 100Hz refresh rate reduces lag and motion blur so you don't miss a thing in fast-paced moments¹
- MORE GAMING POWER: Gain the edge with optimizable game settings; Color and image contrast can be adjusted to see scenes more vividly and spot enemies hiding in the dark; Game Mode adjusts any game to fill the screen so you can view every detail²
- KEEP IT EASY ON THE EYES: Care for your eyes and stay comfortable, even during long sessions; Advanced eye comfort technology certified by TÜV reduces eye strain by minimizing blue light and reducing irritating screen flicker²
- INCREASED VERSATILITY: Connect to more; Plug devices straight into your monitor for increased flexibility, making your computing environment even more convenient
For work in an existing signed-in browser
Claude in Chrome or a carefully configured CDP connection may fit when existing browser state is essential. Confirm the use is allowed by your organization and isolate the session from unrelated accounts. Google notes that an agent with an active authenticated browser can effectively act on the user’s behalf.
Troubleshooting common setup problems
The Playwright command fails or the server does not start
- Check Node.js: Playwright’s official MCP guide requires Node.js 20 or newer. Verify the installed runtime, then retry the command.
- Check package resolution: The command uses
npxand the package name@playwright/mcp. Confirm network access to the package registry and recheck the official installation guide if the package name or command has changed. - Check Claude Code’s MCP registration: Confirm the server was added to the Claude Code environment where you are running the task, rather than to a different project or configuration.
Claude cannot see the browser or the intended page
- Confirm the MCP server or extension is installed, enabled, and available in the active Claude Code session.
- For a live Chromium connection, confirm that the browser is running and the CDP endpoint or channel matches the setup. A configured URL such as
http://localhost:9222must be reachable from the process running the MCP server. - Ask Claude to identify the current page before giving it a multi-step task. This catches an incorrect tab or stale session early.
The site looks different from the test environment
Check whether the task is using a fresh Playwright context or an existing authenticated browser. Cookies, account state, viewport, and the page currently open can change what the agent sees. For a repeatable test, define a consistent test context; for live debugging, verify that the intended account and page are active.
The integration can access more than intended
Disconnect it from a personal profile, move the task to a separate Chrome profile, or use a narrowly scoped test account. If the work is organizational, check administrator rules before using Claude in Chrome or a CDP connection against company accounts.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Screenshot a page without giving Claude control of your browser
If the job is to capture a webpage rather than click through or debug it, a screenshot API is a narrower alternative to browser-control MCP tools. ScreenshotNeo is a website screenshot API and MCP server: it can return PNG, JPEG, WebP, or PDF, and its clean-shot flow accepts cookie/consent banners and removes more than 60 known consent platforms, newsletter popups, and chat widgets before capture. Each cleanup step can be turned off.
For a one-off capture from a terminal, use cURL:
curl -G "https://api.screenshotneo.com/v1/shot" -d access_key=YOUR_API_KEY --data-urlencode url=https://stripe.com -o shot.webpReplace YOUR_API_KEY with your key and change the target URL as needed. The response headers identify the page verdict and whether the request was billed. Bot checks or CAPTCHAs, blank pages, timeouts, failed loads, and cache hits are not billed. See the ScreenshotNeo API documentation for request options.
Best Value
- 【INTEGRATED SPEAKERS】Whether you're at work or in the midst of an intense gaming session, our built-in speakers provide rich and seamless audio, all while keeping your desk clutter-free.
- 【EASY ON THE EYES】 Protect your eyes and enhance your comfort with Blue-Light Shift technology. This feature reduces harmful blue light emissions from your screen, helping to alleviate eye strain during long hours of use and promoting healthier viewing habits.
- 【WIDEN YOUR PERSPECTIVE】Our sleek minimal bezel design ensures undivided attention. The nearly bezel-free display seamlessly connects in a dual monitor arrangement, delivering an unobstructed view that lets you focus on more at once, completely distraction-free.
Python
import requests
r = requests.get(
"https://api.screenshotneo.com/v1/shot",
params={"access_key": "YOUR_API_KEY", "url": "https://stripe.com"},
timeout=90,
)
open("shot.webp", "wb").write(r.content)Node.js
const q = new URLSearchParams({ access_key: 'YOUR_API_KEY', url: 'https://stripe.com' });
const res = await fetch(`https://api.screenshotneo.com/v1/shot?${q}`);The service also supports full-page captures with lazy images loaded, CSS-selector element captures, dark mode, device presets and custom viewports, retina scale, PDF settings, HTML/CSS input, custom CSS and JavaScript, pre-capture clicks, selector hiding, waits, request and resource blocking, custom headers/cookies/user agents/Authorization, timezone and geolocation, transparency, resizing, caching with a chosen TTL, signed public image links, asynchronous jobs with signed webhooks, bulk requests of up to 100 URLs per call, a usage API, and an OpenAPI specification. Its parameter names also work with those used by other screenshot APIs to ease switching.
ScreenshotNeo’s MCP server offers take_screenshot, get_page_info, and capture_pdf for Claude, Cursor, and other MCP clients. It is not a replacement for a browser-control integration when the task requires interacting with an authenticated page, diagnosing live DevTools state, or running browser assertions.
Plans are Free: 1,000 shots per month with no card; Starter: $5 for 3,000; Growth: $15 for 15,000; Pro: $39 for 60,000; Scale: $99 for 250,000; and Business: $249 for 1,000,000. Yearly billing gives two months free. Every feature is available on every plan.
Recommended Free Tools
Or skip the browser setup
Use the API call above when you need a screenshot rather than interactive browser control. Cookie banners, popups, and chat widgets are removed before the shot; bot checks, blank pages, and failed loads are never billed; an MCP server lets AI agents take screenshots; and 1,000 screenshots each month are free with no card, with paid plans starting at $5 for 3,000.
Sign up free for ScreenshotNeo.
Frequently Asked Questions
Can Claude Code control my logged-in Chrome?
Yes, through Claude in Chrome or a carefully configured CDP connection, but the connected agent can access the browser data exposed to it. Use a separate profile or scoped test account rather than a personal profile.
Which option should I use for automated browser tests?
Use Playwright MCP with an isolated browser context for repeatable end-to-end testing. Use Chrome DevTools MCP when the task is to inspect and debug a live Chrome page.
Can I use a screenshot API instead of browser MCP?
Yes, for capturing a page or PDF without interactive browser control. ScreenshotNeo provides an API and MCP server; it does not replace DevTools inspection or browser assertions.
Free tools Windows power users keep installed
One-click scans. No signup required.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
