Setup & Installation
What This Skill Does
Returns how many documents Crawlbase Cloud Storage currently holds for a token. Storage is split per token, so the normal and JS-token silos are counted separately — call once per silo for a grand total.
A cheap sanity check before bulk retrieval or cleanup: agents can size a job and verify writes without listing every rid.
When to use it
- Checking storage usage before running bulk operations
- Answering "how many pages have we stored?" at a glance
- Verifying that a batch of store: true crawls actually landed
- Counting the JS-token silo separately from the normal one
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.