getsnap-mcp
getSnap MCP lets an agent render, compare, and audit web pages in a real browser — returning screenshots inline so the model can actually look at them.
capture_screenshot(1 credit) — render any URL to PNG/JPEG/WebP, full page or viewport, with desktop/mobile/tablet emulation, viewport sizing, and an optional post-load delay; returns the image inline so the model can inspect itcapture_pdf(1 credit) — render any URL to PDF and return a link to it (PDFs can't be shown inline)compare_pages(2 credits) — pixel-diff two URLs and get a similarity score plus a change-overlay image, with an adjustable per-pixel colour threshold; good for staging vs. productionaudit_accessibility(1 credit) — run axe-core in a real browser and get WCAG 2.0/2.1/2.2 violations by severity with the responsible elements, capped bymax_violationscheck_usage(free) — see credits used and remaining on the key this periodDefaults applied everywhere — cookie banners and ad overlays are removed automatically; cached responses cost nothing
Cost-aware — every tool description states its credit cost so an agent can budget before calling; large images fall back to a CDN link instead of flooding context (use
format: "jpeg"orfull_page: falseto keep them inline)Typical uses — catch mobile layout breakage, review a deploy diff, accessibility triage, generate document PDFs, and monitor competitor pages over time
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@getsnap-mcp Screenshot stripe.com on mobile and tell me if anything overlaps."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
getsnap-mcp
Official MCP server for getSnap.dev. Gives Claude and other agents the ability to capture a web page, compare two pages and audit one for accessibility.
The capture tools return the image itself, not a link to it. A model can look at the page it just asked for, so "screenshot this and tell me what's broken" works in a single turn.
Features
capture_screenshot— any URL to PNG, JPEG or WebP, full page or viewport, with mobile and tablet emulation, returned inline so the model can look at itcapture_pdf— any URL to a PDF, returned as a link, since a PDF cannot be shown to a model inlinecompare_pages— visual diff of two URLs: similarity score plus the overlay, inlineaudit_accessibility— axe-core in a real browser: WCAG 2.0/2.1/2.2 violations by severitycheck_usage— credits used and remaining, costs nothingCookie banner removal and ad blocking are on for every capture
Free tier: 100 captures a month, no card
Related MCP server: claude-vision-mcp
Install
No install step. Your client runs it with npx.
Get a free API key at getsnap.dev — 100 captures a month, no card.
Claude Code
claude mcp add getsnap --env GETSNAP_API_KEY=sk_live_... -- npx -y getsnap-mcpClaude Desktop
claude_desktop_config.json:
{
"mcpServers": {
"getsnap": {
"command": "npx",
"args": ["-y", "getsnap-mcp"],
"env": { "GETSNAP_API_KEY": "sk_live_..." }
}
}
}The same block works in any client that speaks MCP over stdio.
Tools
Tool | Credits | Returns |
| 1 | The image, inline |
| 1 | A link — a PDF can't be shown to a model |
| 2 | Similarity score + the diff overlay, inline |
| 1 | WCAG violations by severity |
| 0 | Credits used and remaining |
Cookie banners and ad overlays are removed by default on captures. Cached responses cost nothing and say so.
Things worth knowing
Large images are not inlined. Past about 1.5 MB the capture still
happened and is still on the CDN, so the tool returns the link and says
why. A full_page capture of a long page will usually hit this — pass
format: "jpeg" or full_page: false to get it inline instead.
Every capture spends a credit, so each tool description states its cost. An agent deciding whether to call something should be able to see what it will cost before it does.
compare_pages costs 2, because it launches a browser per URL.
Configuration
Variable | Required | Default |
| yes | — |
| no |
|
Without a key the server exits immediately with a message explaining where to get one, rather than starting and failing on first use.
Examples
Once connected, ask your agent in plain language:
"Screenshot stripe.com on mobile and tell me if anything overlaps."
"Compare our staging site against production and show me what moved."
"Audit example.com for accessibility and list the critical failures."
"How many getSnap credits do I have left?"
Use cases
Catch layout breakage — screenshot a page at mobile width and have the model describe what overlaps or clips
Review a deploy — diff staging against production and see what moved before anyone else does
Accessibility triage — list WCAG failures by severity ahead of a release
Generate documents — turn an invoice, report or receipt URL into a PDF
Watch a competitor — capture a pricing page on a schedule and compare it with last week's
Links
Versioning
This package versions independently of the getSnap REST API and the Node and Python SDKs. It shared their number until 1.14.3, when it moved out of the API monorepo into this repository; from here it moves on its own schedule.
MIT licensed. Issues to support@getsnap.dev.
Available Tools
5 toolsaudit_accessibilityAudit a page for accessibility problemsARead-only
Run axe-core against a URL in a real browser and return WCAG 2.0/2.1/2.2 violations by severity, with the elements responsible. Costs 1 credit per call. Returns structured findings rather than an image, so you can act on them directly.
Inputs: url (required), max_violations.
capture_pdfCapture a page as PDFARead-only
Render a URL to PDF and return a link to it. Costs 1 credit per call. A PDF cannot be shown to you inline - use capture_screenshot if you need to read the page yourself.
Inputs: url (required), delay, full_page.
capture_screenshotCapture a screenshotARead-only
Render a URL in a real browser and return the image, so you can see the page. Removes cookie banners and ad overlays by default. Costs 1 credit per call. Use full_page for the whole scrollable page, or device to emulate a phone or tablet.
Inputs: url (required), delay, device, format, +4 more.
check_usageCheck remaining creditsARead-only
How many credits are used and remaining on this key this period. Free - spends no credit.
Inputs: no named parameters.
compare_pagesCompare two pages visuallyARead-only
Capture two URLs and compare them pixel by pixel. Returns a similarity score and an overlay image marking what changed, which you can look at. Costs 2 credits - it launches a browser per URL. Use for staging against production, or a page before and after a change.
Inputs: after_url (required), before_url (required), full_page, threshold.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: capture (screenshot/pdf), compare two pages, audit accessibility, and check credits. The only potential overlap—capture_screenshot vs capture_pdf vs compare_pages, all of which render URLs—is resolved explicitly in descriptions (e.g., PDF can't be shown inline, compare diffs two pages).
All tools follow a consistent snake_case verb_noun convention: compare_pages, audit_accessibility, capture_screenshot, capture_pdf, check_usage. The shared capture_ prefix is used sensibly for the two rendering tools.
Five tools is well-scoped for a page-capture/audit service, with no filler. Each tool earns its place and covers a distinct capability.
Core lifecycle is covered: screenshot, PDF, comparison, accessibility audit, and credit usage. Minor gaps exist (e.g., no HTML/text extraction or element-scoped capture beyond device/full_page params), but agents can work around these.
Related MCP Connectors
Give your agent eyes: screenshots of any web page it can see, pages as markdown, and PDFs.
A real browser for your agent: screenshots, page checks, Markdown and PDFs.
Screenshot, PDF and HTML-to-image rendering API so Claude and Cursor can see any web page.
Screenshot, PDF and HTML-to-image rendering API so Claude and Cursor can see any web page.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables Claude Code to capture and analyze web page screenshots, responsive layouts, and page metadata using Puppeteer. It allows developers to perform visual UI inspections and compare designs across various viewports directly within the terminal.3MIT
- AlicenseAqualityDmaintenanceEnables Claude to capture screenshots of the screen, windows, regions, and web pages, and compare screenshots for visual regression testing.6MIT
- AlicenseAqualityBmaintenanceEnables AI agents to capture screenshots, scrape structured page content, and run automated visual checks on live websites via a headless Chromium browser.3MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI vision workflows to capture fresh webpage screenshots, specific DOM elements, and timed screencasts, automatically limiting resolution and tiling full pages into 1072x1072 chunks for LLM-friendly processing.-