Skill
firecrawl
API for interacting with Firecrawl services to perform web scraping and crawling tasks.
When to use firecrawl
Choose if
You want Firecrawl's managed scraping pipeline (scrape, crawl, extract, search, deep research, LLMs.txt) inside an agent loop with typed CLI ergonomics, credit-tracking commands, and async crawl-job management. Alternative is the raw Firecrawl REST API, which gives you the endpoints but no credit-monitoring helpers or job-cancel affordances out of the box.
Avoid if
You don't have a Firecrawl account (the upstream is not free and the README does not disclose pricing). Also avoid for self-hosted scraping, captcha-walled targets that need full browser automation, or BR-specific public-portal flows where the auxiliar `br_portal/*` stateful runtime is the right tool.
Risk Flags
- MEDIUM auth Requires a Firecrawl API key tied to a Firecrawl account. Credit/token consumption is exposed via dedicated commands but the README discloses no concrete pricing — users must check the Firecrawl dashboard for plan and per-page cost.
- LOW scope Wraps the Firecrawl SaaS API. For self-hosted scraping or headless-browser control you want a different tool (Playwright, Puppeteer, the auxiliar br_portal runtime).
Cost
Type: Unknown
Install
Default
npx -y @mvanhorn/printing-press install firecrawl
Estimated time to first success: ~10 min
Dependencies
Minimum runtime: Node.js (npx) or Go 1.26.3+ for source install; Claude Desktop 1.0.0+ for MCPB bundle
Distribution
- Repository
- https://github.com/mvanhorn/printing-press-library
- License
- MIT