Use GetScreenshot in Cursor
Add the GetScreenshot MCP server to mcp.json. Cursor's agent can then capture any public page, render HTML it just wrote, and compare before and after.
Works with any GetScreenshot API key on any plan, from $5/month.
What you get
Five tools that let the agent look at web pages
Look at any public page
The agent passes a URL to capture_screenshot. A hosted browser renders the page and the tool returns images sized for vision models, plus a link to the full-resolution file.
Render HTML it just wrote
render_html takes an HTML string and returns a screenshot of it. The agent can check a component or email template without a local browser.
Compare before and after
compare_screenshots diffs two pages or two earlier captures and reports the share of changed pixels, where the change is, and a diff image.
Limits worth knowing: captures run on our servers, so they cannot reach localhost or private networks. Each call is a single capture, not a logged-in browsing session. For multi-step browser automation see GetScreenshot vs Playwright MCP. Screenshot links are public URLs that stay available for 30 days.
Before You Start
Three things to have ready
A GetScreenshot API key
Any plan works. Plans start at $5/month for 2,500 screenshots. Get a key.
Cursor
Cursor installed.
Node.js 20.9 or newer
Only for the local option, which runs npx -y getscreenshot-mcp on your machine. The hosted option needs nothing installed.
How to Set Up
Hosted server at https://mcp.getscreenshotapi.com/mcp, or a local server started with npx
Cursor supports both connection styles. Use one of them, not both. Both give the agent the same five tools and use the same API key and quota.
Get your API key
Pick a plan on the pricing page. The key arrives by email after checkout. The MCP server works with any API key on any plan, including Lincoln at $5/month for 2,500 screenshots. Code FREE5 makes the first month of the $5 plan free. If you lose the key, recover it from your account page.
View pricing plansPut the key in an environment variable
Set GETSCREENSHOT_API_KEY once, so the config below can reference the key instead of containing it. On macOS and Linux, add this line to your shell profile (~/.zshrc or ~/.bashrc). On Windows, add it as a user environment variable.
export GETSCREENSHOT_API_KEY=YOUR_API_KEYRestart Cursor after you set the variable so it picks up the new value. Cursor resolves ${env:NAME} in the command, args, env, url and headers fields of mcp.json.
Option A: connect to the hosted server
Nothing to install. Create or edit ~/.cursor/mcp.json in your home directory to use the server in every project, or .cursor/mcp.json in a project folder to use it there only.
~/.cursor/mcp.json
{
"mcpServers": {
"getscreenshot": {
"url": "https://mcp.getscreenshotapi.com/mcp",
"headers": {
"Authorization": "Bearer ${env:GETSCREENSHOT_API_KEY}"
}
}
}
}If the file already has an mcpServers object, add the getscreenshot entry inside it.
Option B: run the server locally
Cursor starts the server on your machine with npx. Needs Node.js 20.9 or newer.
~/.cursor/mcp.json
{
"mcpServers": {
"getscreenshot": {
"command": "npx",
"args": ["-y", "getscreenshot-mcp"],
"env": {
"GETSCREENSHOT_API_KEY": "${env:GETSCREENSHOT_API_KEY}"
}
}
}
}The project file .cursor/mcp.json is meant to be committed so teammates get the same tools. The ${env:...} reference keeps the key out of it. If you would rather paste the key directly, do that only in ~/.cursor/mcp.json in your home directory, and never commit a file that contains it.
Confirm it is connected
Save the file and restart Cursor. Open Customize in the sidebar and click MCPs. getscreenshot should be listed with its toggle on. The same toggle turns the server off without removing it.
Try a prompt
Ask the agent for a screenshot of a public page. Cursor asks for approval before it runs an MCP tool by default. Click the arrow next to the tool name to see the arguments.
Take a screenshot of https://example.com and describe what is above the fold.Prompts to Try
Replace the example URLs and file names with your own
Check a deployed change
Take a full-page screenshot of https://example.com/pricing and list anything that looks broken or misaligned.
Check HTML you just wrote
Render the HTML in components/pricing-card.html with render_html and tell me whether the spacing looks right.
Compare staging and production
Compare https://staging.example.com with https://www.example.com and describe what changed.
Check a mobile layout
Capture https://example.com with the iphone12 device and tell me if the navigation fits on screen.
Each page captured uses one screenshot from your monthly quota. A comparison uses one per page it has to capture.
Tools the Server Adds
All five are read-only. Full inputs and outputs are in the MCP server reference
| Tool | What it does |
|---|---|
| capture_screenshot | Capture a public web page as images the model can see. Options cover full-page capture, a single element by CSS selector, device presets and wait conditions. |
| render_html | Render an HTML string (up to 2 MB) and screenshot it. Useful for a component or page the agent just wrote. |
| compare_screenshots | Visual diff of two pages or two earlier screenshots. Returns the changed-pixel percentage, the bounding box of the change and a diff image. |
| capture_pdf | Save a page as an A4 PDF and return a link that works for 30 days. |
| get_usage | Screenshots used, monthly limit and reset date for your key. Costs 1 quota unit. |
Troubleshooting
Common issues and how to resolve them
Tools say no API key is configured, or the hosted server rejects the request
- • Check that
GETSCREENSHOT_API_KEYis set in the environment Cursor runs in, then restart Cursor. - • Check the spelling of the reference:
${env:GETSCREENSHOT_API_KEY}. - • Open the Output panel (Cmd+Shift+U) and select MCP Logs from the dropdown to see connection and authentication errors.
The server is not listed
- • Check that
mcp.jsonis valid JSON and thatgetscreenshotsits insidemcpServers. - • Restart Cursor after every edit to the file.
- • Local setup: run
node --versionin a terminal. It should print v20.9 or newer.
A tool call times out on a slow page
- • Ask the agent to retry with
wait_until: "domcontentloaded". It is the fastest setting and the most reliable on heavy sites. - • A capture usually takes around 9 seconds. The API gives up after 90 seconds.
- • Failed captures still count against your monthly quota, so change the settings before retrying more than once.
The agent cannot capture localhost or an internal site
- • The capture runs on our servers, which cannot reach
localhostor private networks. - • For markup the agent just wrote, use
render_htmlwith the HTML itself. Inline the CSS and images or set<base href>, because relative asset URLs will not resolve. - • For a running app, give the agent a public preview URL or a tunnel address.
The image is too large for the conversation
- • Ask for
return: "url_only"to get thescreenshot_urlwithout inline images. - • Capture one part of the page with
elementand a CSS selector instead of the full page. - • Lower
max_slices(default 4) to limit how many images a full-page capture returns. - • Cursor attaches returned images to the chat. The model only reads them if it supports image input, so pick a model that does.
Still stuck? Email support@rasterwise.com.
Other AI Clients
The same server works in other MCP clients. See all options on the AI Agents page
Prefer instructions the agent loads on demand? See the GetScreenshot agent skill.
GetScreenshot is an independent product. It is not affiliated with or endorsed by the makers of Cursor. Product names belong to their owners.
Get an API Key and Connect Cursor
Plans start at $5/month for 2,500 screenshots. The MCP server works with any API key on any plan.