Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Fix the driver behind crashes, sound loss and screen glitches3Clear out junk files and repair common Windows errorsPuppeteer MCP lets an MCP-capable assistant use browser tools to navigate pages, interact with controls, inspect content, and capture screenshots. To get started, install the server, add it to your AI client’s MCP configuration, reload the client, then use a repeatable sequence: navigate, wait for the page state you need, interact, and capture. The exact configuration file and available tools depend on the MCP client and server implementation.
What Puppeteer MCP does
Puppeteer is a JavaScript library for controlling Chrome or Firefox through the Chrome DevTools Protocol (CDP) or WebDriver BiDi. It runs headless by default and can navigate pages, interact with web interfaces, generate PDFs, and take screenshots. Puppeteer MCP adds a tool interface that lets an MCP-compatible assistant request browser actions instead of requiring you to write a script for every task.
The documented server exposes browser operations such as navigation, screenshots, JavaScript execution, and configurable launch options. Other community implementations may also offer clicks, form filling, hover, cookies, request interception, console logs, or connection to an existing Chrome instance. Do not assume every server exposes the same tools or accepts the same arguments: inspect the tools shown by your client after connecting.
MCP is the connection layer, not a replacement for the browser. The browser still has to launch somewhere—on your computer, in a container, or in another managed environment—and the server determines which operations the assistant can call.
Windows 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 reinstallCrashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minute#1 Best Overall
- Compatible with Nintendo Switch 2’s new GameChat mode
- Auto-Light Balance: RightLight boosts brightness by up to 50%, reducing shadows so you look your best—compared to previous-generation Logitech webcams (1)
- Privacy with a Slide: The integrated webcam cover makes it easy to get total, reliable privacy when you're not on a video call
- Built-In Mic: The built-in microphone lets others hear you clearly during video calls
- Easy Plug-And-Play: The Brio 101 works with most video calling platforms, including Microsoft Teams, Zoom and Google Meet—no hassle; it just works
Install Puppeteer and the MCP server
- Install Node.js. Use a supported Node.js installation and open a terminal in the project or working directory where you want to manage browser automation.
- Install Puppeteer if you also need direct scripts. Run
npm i puppeteer. Puppeteer normally downloads a compatible Chrome during installation. If package-manager scripts are disabled, or the browser is missing later, runnpx puppeteer browsers installto install the browser binary. - Add the MCP server to your client. A commonly documented npx configuration pattern is shown below. Put an equivalent object in your MCP client’s configuration file; the file’s location and surrounding settings vary by client.
{
"mcpServers": {
"puppeteer": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-puppeteer"]
}
}
}- Reload the client. Restart or reload the MCP integration as required by that client, then check that Puppeteer tools appear in its available-tool list. If they do not, check the client’s MCP configuration syntax and whether it can start
npx. - Choose a launch mode deliberately. Headless mode is suitable for unattended work and CI. A visible browser can make selector and timing problems easier to diagnose. Use the launch options supported by the server you installed rather than assuming options from another implementation will work.
A Docker deployment is another documented pattern: use the mcp/puppeteer image with DOCKER_CONTAINER=true. Container setup also requires a usable browser executable and appropriate sandbox and shared-memory settings; use the image’s own instructions for its exact invocation.
Run a repeatable browser task through MCP
Begin with a small task so you can verify that the server is connected and that each tool call produces the expected state. For example, a navigation followed by a full-page screenshot can be expressed as:
Rank #2
- 1080P Webcam with Cover for Video Calls - EMEET computer webcam provides design and Optimization for professional video streaming. Realistic 1920 x 1080p video, 5-layer anti-glare lens, providing smooth video. C960 computer camera delivers 1920x1080 video with fixed focus (11.8–118.1 inches), so as to provide a clearer image. C960 USB webcam has a cover and can be removed automatically to meet your needs for privacy. For optimal image performance, use the webcam in a well-lit environment.
- Built-in 2 Omnidirectional Mics - EMEET webcam with microphone for desktop features 2 built-in omnidirectional microphones, picking up your voice to create clear audio for communication. When installing the webcam, select EMEET C960 as the default microphone input device in your computer and video applications and select C960 as the default device in Zoom/Teams and ensure microphone permissions are enabled for proper use. Please note that C960 does not include built-in speakers.
- Automatic Light Adjustment - Automatic exposure adjustment is applied in EMEET HD webcam 1080p so that the streaming webcam can deliver stable image performance. EMEET C960 camera for computer also features color adjustment and exposure optimization to help you look your best. For optimal video quality, it is recommended to use the webcam in normal or well-lit environments and select suitable video settings in your application. Proper lighting helps achieve a clearer and more balanced image.
- Plug-and-Play & Upgraded USB Connectivity - New C960 webcam features both USB Type-A & A-to-C adapter connections for wider compatibility. For stable performance, connect the webcam directly to the computer's main USB port and ensure the device is recognized correctly. If a hub or docking station is used, please ensure it provides sufficient power and stable data transmission, as limited ports may affect performance. 90° wide-angle lens captures more participants without frequent adjustments.
- High Compatibility & Multi Application - C960 webcam for laptop is compatible with Windows 10/11, macOS 10.14+, and Android TV 7.0+. Not supported: Windows Hello, TVs, tablets, or game consoles. It works with Zoom, Teams, Facetime, Google Meet, YouTube and more. Please select C960 webcam as the default camera and microphone device in your application and ensure camera/microphone permissions are enabled, especially on macOS. (Tips: Incompatible with Windows Hello)
puppeteer_navigate({"url":"https://example.com"})
puppeteer_screenshot({"name":"example-home","fullPage":true})These names and arguments illustrate the documented tool-oriented sequence; a particular client may display a different schema. Use the names and required fields shown in its tool descriptions.
For an interaction, use this order:
- Navigate to the page you want to automate.
- Set or confirm the viewport before comparing layouts or saving screenshots. Consistent viewport dimensions make repeated captures easier to compare.
- Locate the control using a stable selector or an accessible name. Prefer semantic locators over generated class names that may change between page builds.
- Fill or click the control, then wait for an observable result—such as a confirmation message or results panel—rather than assuming the action succeeded.
- Read or inspect the resulting state if the task depends on page content, then capture the screenshot.
For instance, tell the assistant to open a form page, fill the email field, submit it, wait until the confirmation element is visible, and capture the resulting screen. This gives the automation a verifiable stopping point. If a form has multiple controls with similar labels, specify the page context or a more precise locator rather than asking the assistant to click an ambiguous button.
Rank #3
- 【Full HD 1080P Webcam】Powered by a 1080p FHD two-MP CMOS, the NexiGo N60 Webcam produces exceptionally sharp and clear videos at resolutions up to 1920 x 1080 with 30fps. The 3.6mm glass lens provides a crisp image at fixed distances and is optimized between 19.6 inches to 13 feet, making it ideal for almost any indoor use.
- 【Wide Compatibility】Works with USB 2.0/3.0, no additional drivers required. Ready to use in approximately one minute or less on any compatible device. Compatible with Mac OS X 10.7 and higher / Windows 7, 8, 10 & 11 / Android 4.0 or higher / Linux 2.6.24 / Chrome OS 29.0.1547 / Ubuntu Version 10.04 or above. Not compatible with XBOX/PS4/PS5.
- 【Built-in Noise-Cancelling Microphone】The built-in noise-canceling microphone reduces ambient noise to enhance the sound quality of your video. Great for Zoom / Facetime / Video Calling / OBS / Twitch / Facebook / YouTube / Conferencing / Gaming / Streaming / Recording / Online School.
- 【USB Webcam with Privacy Protection Cover】The privacy cover blocks the lens when the webcam is not in use. It's perfect to help provide security and peace of mind to anyone, from individuals to large companies. 【Note:】Please contact our support for firmware update if you have noticed any audio delays.
- 【Wide Compatibility】Works with USB 2.0/3.0, no additional drivers required. Ready to use in approximately one minute or less on any compatible device. Compatible with Mac OS X 10.7 and higher / Windows 7, 10 & 11, Pro / Android 4.0 or higher / Linux 2.6.24 / Chrome OS 29.0.1547 / Ubuntu Version 10.04 or above. Not compatible with XBOX/PS4/PS5.
Take full-page and element screenshots
Puppeteer can capture a visual snapshot of a whole page or a specific element. With MCP, request the target URL or existing page, the viewport dimensions, whether the capture should include the full page, and the expected output form—such as an inline image, file, or encoded data—using the server’s actual tool schema.
- Full-page capture: Use it for documentation or an archival view of a long page. Long pages may contain lazy-loaded images, so scroll or wait for relevant content before capture if the server does not do so automatically.
- Element capture: Use a CSS selector when you need a focused component rather than the whole page. Confirm that the selector matches the intended element before treating the image as complete.
- Repeatable layout capture: Set a deterministic viewport, wait for fonts and images, and let dynamic content reach the intended state. On a page you control, disabling transitions can reduce visual differences between captures.
If the page includes animation or asynchronous content, capture only after the relevant UI has settled. A screenshot taken immediately after navigation may be valid as an image but still show a loading state, incomplete text, or missing images.
Rank #4
- Compatible with Nintendo Switch 2’s new GameChat mode
- Crisp HD 720p/30 fps video calls with diagonal 55° field of view and auto light correction. Compatible with popular platforms including Skype and Zoom.
- The built-in noise-reducing mic makes sure your voice comes across clearly up to 1.5 meters away, even if you’re in busy surroundings.
- C270’s RightLight 2 feature adjusts to lighting conditions, producing brighter, contrasted images to help you look good in all your conference calls.
- The adjustable universal clip lets you attach the camera securely to your screen or laptop, or fold the clip and set the webcam on a shelf. You’re always ready for your next video call.
Write a direct Puppeteer script when you need tighter control
MCP is useful when an assistant should decide or perform browser actions interactively. A direct script is often preferable when you need a repeatable job, explicit control flow, or a saved image at a known path. This runnable example uses Puppeteer’s locator workflow to navigate, fill a form, wait for a result, take a full-page screenshot, and close the browser:
const puppeteer = require('puppeteer');
(async () => {
const browser = await puppeteer.launch({ headless: true });
try {
const page = await browser.newPage();
await page.setViewport({ width: 1365, height: 900 });
await page.goto('https://example.com', { waitUntil: 'domcontentloaded' });
// Replace these selectors with controls that exist on your target page.
await page.locator('input[type="email"]').fill('[email protected]');
await page.locator('button[type="submit"]').click();
await page.locator('[data-testid="confirmation"]').wait();
await page.screenshot({ path: 'page.png', fullPage: true });
} finally {
await browser.close();
}
})().catch((error) => {
console.error(error);
process.exitCode = 1;
});Save it as a JavaScript file and run it with Node.js from the directory where Puppeteer is installed. The example’s form selectors and confirmation selector are placeholders for page-specific elements; replace them with selectors that actually exist. If your target has no form, remove the interaction and wait for an element or state that signals the page is ready to capture.
Best Value
Local, container, and hosted execution
Local Puppeteer gives you direct control over browser launch, page actions, and files, but you own browser installation and environment configuration. It is a natural fit for development and scripts or CI environments where you can maintain the browser binary. A visible browser is useful for debugging; headless execution is generally more convenient for unattended tasks.
A container can make the runtime more consistent across machines, but it adds container configuration and requires attention to browser paths, shared memory, and sandbox settings. A hosted browser MCP can shift browser maintenance to a provider, but its availability, data handling, network access, latency, pricing, and any third-party terms need to be checked with that provider. The choice is a trade-off among setup work, debugging access, isolation, networking, and cost; there is no universally best execution location.
Troubleshooting Puppeteer MCP
| Symptom | Likely cause | What to check |
|---|---|---|
| The MCP client shows no Puppeteer tools | The server did not start, or the client configuration is misplaced or invalid. | Check the client’s MCP configuration format and logs, confirm that npx is available to the client process, and reload the integration after editing. |
| Browser launch fails after installation | The compatible browser binary is absent, often because install scripts were blocked. | Run npx puppeteer browsers install, then check that the runtime can access the installed executable. |
| A container starts but Chromium exits | Browser executable path, shared memory, or sandbox settings may not match the container environment. | Verify the image and executable path, check available shared memory, and use only the sandbox configuration required for that environment. |
| A click or form fill has no effect | The selector may be stale or ambiguous, the element may not yet be ready, or the page may have changed state. | Use a stable semantic locator, wait for the target element, and inspect the page text or console output to see what happened. |
| The screenshot shows a loading state or missing content | The page was captured before asynchronous content, fonts, images, or lazy-loaded sections were ready. | Wait for a meaningful selector or page state; for long pages, ensure the relevant lazy content has been loaded before capturing. |
| Visual output differs after blocking requests | Request interception may have blocked scripts or stylesheets that affect rendering. | Allow the resources needed for the intended visual state, then capture again. |
Security and reliability considerations
- Keep the browser debugging endpoint private. Do not expose a connection to an existing Chrome instance on an untrusted network.
- Avoid dangerous launch arguments unless your environment requires them. Some MCP implementations document an
allowDangerouscontrol; its behavior is implementation-specific. - Give the assistant only the browser capabilities and access needed for the task. Pages can contain untrusted content, and browser automation can submit forms or trigger state changes.
- Prefer waiting for a meaningful selector or page state over adding arbitrary sleeps. When a task fails, use page text and console output to distinguish a navigation problem from a selector or application error.
- For visual comparisons, keep viewport and page state consistent. Blocking scripts or styles may speed loading but can also change the page being measured.
Or skip the browser setup
If your task is to retrieve a screenshot or PDF rather than interact with a live browser, ScreenshotNeo provides a website screenshot API and MCP server. One GET request can return a screenshot or PDF; the following cURL example saves a WebP screenshot of Stripe:
curl -G "https://api.screenshotneo.com/v1/shot" -d access_key=YOUR_API_KEY --data-urlencode url=https://stripe.com -o shot.webpSee the ScreenshotNeo API documentation for request options. It removes cookie/consent banners, newsletter popups, and chat widgets before the shot; bot checks, blank pages, failed loads, timeouts, and cache hits are not billed. Its MCP server gives AI agents screenshot tools, and the free plan includes 1,000 screenshots a month without a card; paid plans start at $5 for 3,000 screenshots. Sign up for the free plan.
Free tools Windows power users keep installed
One-click scans. No signup required.
Frequently Asked Questions
Can this MCP setup automate Firefox?
Puppeteer itself supports Chrome and Firefox through CDP or WebDriver BiDi, but support in a particular Puppeteer MCP server depends on that server’s implementation and launch options. Check the tools and configuration offered by the server you install.
Can I connect Puppeteer MCP to an already running Chrome instance?
Some community implementations support connecting to an existing browser. Whether yours does depends on its configuration; protect the debugging endpoint and do not expose it to untrusted networks.
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.
