Snapgrab

quartzunit/snapgrab

Wraps Playwright's headless browser into three MCP tools for screenshot capture and metadata extraction. You get capture_screenshot for single viewports, capture_comparison for desktop vs mobile diffs, and extract_page_metadata when you just need titles and Open Graph tags. Images are automatically resized to 1568px width for Claude Vision with token cost estimates included in the response. Ships with viewport presets, full page capture, CSS selector targeting, and dark mode forcing. Built on a standalone Python library if you want to use it outside MCP. Reach for this when you need Claude to see live web pages instead of just reading HTML or relying on descriptions.

tools

3

transport

STDIO

last updated

Mar 17, 2026

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

from snapgrab import capture

result = await capture("https://example.com")
print(result.path)           # /tmp/snapgrab/example_com_desktop_20260317_120000.png
print(result.metadata.title) # "Example Domain"
print(result.vision_tokens)  # ~2764