To screenshot a website with Gemini CLI, connect it to a browser-control MCP server, ask Gemini to open the target URL and capture the page, then verify whether the screenshot was returned to the chat, saved to disk, or both. You can configure Chrome DevTools MCP yourself, or use Gemini CLI’s documented browser agent, which launches its bundled browser server. These are separate setup routes; choose one and follow its current documentation.
Choose a setup route
| Route | How it works | Best fit |
|---|---|---|
| Configure Chrome DevTools MCP directly | You add a server configuration to Gemini CLI and manage its browser executable and options. | You want explicit control over the MCP server configuration. |
| Gemini CLI browser agent | You enable the browser agent; Gemini CLI launches its bundled chrome-devtools-mcp server and manages the browser session. |
You want the CLI’s managed browser workflow and session modes. |
Gemini CLI supports MCP servers and exposes their tools to the model. Its MCP documentation also explains that server instructions can be appended to the system instructions: MCP servers with Gemini CLI. For commands and tool behavior, see the tools reference and CLI commands.
As an Amazon Associate I earn from qualifying purchases.
Route A: Configure Chrome DevTools MCP directly
1. Check your browser and project
Install Gemini CLI, Chrome or another browser supported by the selected Chrome DevTools MCP setup, and the project or website you want to capture. If the target is a local app, start it using the project’s own instructions and note its local URL. The Google Codelab’s configuration is an example, not a universal command: executable paths, package versions, operating systems, browser installations, authentication, and headless support vary. Its exercise also notes that BrowserMCP will not work from Google Cloud Shell in that described setup. Consult the Google Codelab and the chosen server’s current instructions before adapting its configuration.
The Tool Desk
Outbyte Driver Updater FREEScan for outdated or missing drivers - takes under a minuteDriver Scan →Outbyte PC Repair FREERepair Windows errors before they cause bigger problemsFix Now →2. Add the server configuration
The Codelab demonstrates a mcpServers entry named chrome-devtools that runs chrome-devtools-mcp@latest with a Chrome executable path and the --headless option. Use the Codelab’s current example as the starting point and replace the executable path with the path for your own browser installation. Do not copy an example path blindly: an incorrect path or unsupported headless setup can prevent the server from starting.
#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
3. Start Gemini CLI and check the server
- Run
geminiin the project directory after saving the MCP configuration. - At the Gemini CLI prompt, run
/mcp listto check whether the server and its tools are available. - If the server is missing, review the CLI’s startup output and configuration, and verify the executable path and server package setup.
4. Ask for a screenshot and a file path
Use a prompt that identifies both the page and the desired output. For example:
Open https://example.com with the configured Chrome DevTools MCP tools, wait for the page to finish loading, take a screenshot, and save it as output/site.png. Tell me where the file was saved.
Rank #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
Replace the example URL and path. If you are capturing a local app, start it first and use its actual local URL. Gemini may ask for approval before an MCP action; review the requested action and approve it only if you intend to allow it. The Codelab’s example asks Gemini to inspect a dashboard and save output/dashboard.png; treat that as the example’s requested destination, not a guarantee that every task writes there.
Recommended Free Tools
Route B: Use Gemini CLI’s browser agent
The browser agent is a distinct route from adding the MCP server directly. The official documentation describes enabling browser_agent in settings.json; the bundled chrome-devtools-mcp server is then launched automatically. Follow the live Browser Agent documentation for the setting’s current location and syntax, because configuration details and prerequisites can change.
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.
Pick the browser session mode
| Mode | Behavior | Use it when |
|---|---|---|
persistent |
The default mode; retains a browser profile. | The task needs browser state retained across sessions. |
isolated |
Uses a temporary profile. | You want a cleaner temporary session rather than retained profile state. |
existing |
Attaches to a Chrome instance with remote debugging enabled. | You need to use an already-running, remotely debuggable Chrome instance. |
The browser-agent documentation currently states a Chrome minimum version of 144 or later. Because this requirement is version-sensitive, check the live documentation before setup. It also describes optional visual-agent support through visualModel for screenshot analysis and visual-identification tasks. That optional capability needs API-key or Vertex AI authentication and is unavailable with “Sign in with Google,” according to the same documentation.
Know what “screenshot” means in an MCP workflow
A screenshot returned in an MCP tool response and a screenshot file written to disk are different outputs. Gemini CLI’s MCP guide describes tool results that can include text and image blocks. An image block can contain type: "image", base64-encoded data, and an image MIME type such as image/png; Gemini CLI makes the text available to the model and displays image data separately. That response does not, by itself, prove that a PNG file was saved to your machine. See the official MCP server guide.
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
- If you want Gemini to inspect the screenshot, ask it to capture the page and describe what it sees; ensure the selected tool returns image content or supports visual analysis.
- If you need a file, name the destination path explicitly and ask Gemini to confirm the saved path.
- If you need both, state that you want the image returned for inspection and saved to a path, then verify each result independently.
Verify the output
- Check Gemini’s response for a specific confirmation of the output path; do not infer that the file exists merely because an image appeared in the conversation.
- Open the destination directory and confirm the file is present and non-empty.
- Open the image to check that it shows the intended page rather than a loading state, error screen, or unexpected browser content.
- If the capture is wrong, refine the prompt with the exact URL, a wait condition, and any interaction needed before capture. For a local app, check that the app is still running and reachable from the browser environment.
Common problems and fixes
| Symptom | Likely cause | What to check |
|---|---|---|
/mcp list does not show Chrome DevTools tools |
The server configuration was not loaded, or the server failed to start. | Check the configuration location and syntax, CLI startup output, package setup, and browser executable path. Compare your setup with the current Codelab example. |
| The browser will not launch | The configured executable path is wrong, the browser is unavailable in the environment, or the selected headless option is unsupported there. | Verify the browser installation and path for your OS and environment; confirm the chosen server supports the launch options you configured. |
| The screenshot shows a blank, loading, or incomplete page | The page may not have finished loading, the app may not be running, or the capture happened before content appeared. | Check the URL from the browser environment, start the app if needed, and ask Gemini to wait for the page or a specific visible element before taking the screenshot. |
| Gemini displays an image, but there is no file | The tool returned image content without writing a file. | Ask for a disk destination explicitly and verify the file at that path. |
| The output file is missing or in a different directory | The prompt did not specify a path clearly, or the tool used a different working directory. | Use a clear relative or absolute destination and ask Gemini to state the path it wrote. Then inspect that location. |
| The browser agent or visual analysis cannot start | A prerequisite may be unmet, such as the documented Chrome version or supported authentication for the optional visual agent. | Check the current Browser Agent documentation; distinguish the browser-agent setup from optional visual-agent authentication. |
| The workflow fails in a hosted or remote environment | The environment may not provide a compatible browser or support the needed launch mode. The Codelab specifically cautions that BrowserMCP will not work from Google Cloud Shell in its described exercise. | Use an environment with a supported browser setup, or consult the selected MCP server’s requirements before changing the workflow. |
Or skip the browser setup
If you only need a website screenshot, ScreenshotNeo is a screenshot API and MCP server. Its API takes a URL in one GET request and can return PNG, JPEG, WebP, or PDF. For an API call, see the ScreenshotNeo documentation.
cURL
curl -G "https://api.screenshotneo.com/v1/shot" -d access_key=YOUR_API_KEY --data-urlencode url=https://example.com -o shot.webp
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://example.com"}, timeout=90)
open("shot.webp", "wb").write(r.content)
Node.js
const q = new URLSearchParams({ access_key: 'YOUR_API_KEY', url: 'https://example.com' });
const res = await fetch(`https://api.screenshotneo.com/v1/shot?${q}`);
Quick Recap
Replace YOUR_API_KEY with your key and https://example.com with the target URL. ScreenshotNeo accepts consent banners before capture and removes more than 60 known consent platforms, newsletter popups, and chat widgets; each of those steps can be turned off. Bot checks, blank pages, timeouts, failed loads, and cache hits are not billed, and response headers identify the page verdict and billing status. Its MCP server includes take_screenshot, get_page_info, and capture_pdf for Claude, Cursor, and other MCP clients. The Free plan includes 1,000 screenshots per month with no card; paid plans start at $5 for 3,000 shots. Sign up for free: 1,000 screenshots a month, no card required.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
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.
