Setup & Installation
What This Skill Does
Captures a screenshot of any webpage through the crawl_screenshot tool of the Crawlbase MCP server. Supports full-page or viewport mode, desktop and mobile devices, custom dimensions, and page-load wait tuning. The underlying page can optionally be pushed to Crawlbase Cloud Storage while the screenshot URL is returned.
Visual evidence without running a browser yourself: JS rendering and anti-bot handling happen on Crawlbase infrastructure, and your agent gets back an image URL it can attach or analyze.
When to use it
- Verifying a landing page looks right after a deploy
- Capturing how a page renders on mobile versus desktop
- Documenting what a page looked like at a point in time
- Sharing a visual preview of a page in a report or chat
- Giving UI-aware agents an image they can analyze
More from Crawlbase
The MCP server behind these skills (npm @crawlbase/mcp). Connects AI agents and LLMs to real-time web data with JavaScript rendering, automatic proxy rotation, and anti-bot protection. Works with Claude, Cursor, and Windsurf.
LangChain document loader, tool, and retriever backed by the Crawlbase Crawling API. Returns clean Markdown documents ready for chunking (pip install langchain-crawlbase).
Native Crawlbase node for n8n. Adds Crawling API credentials and options like JS rendering, geo-targeting, screenshots, and storage to your workflows without hand-wiring HTTP Request nodes.