76 /100
Good for approved web extraction, but crawling scope and API keys need clear limits.
Structured output 82/100
Whether the CLI can return JSON, YAML, or stable machine-readable output.
Non-interactive use 76/100
Whether common workflows can run predictably without an interactive prompt.
Safety boundaries 54/100
Whether read-only, dry-run, scoped auth, and destructive command boundaries are clear.
Install options
npx
$ npx firecrawl Common commands
Crawl a page · requires review
$ npx firecrawl crawl https://example.com Fetches web content for downstream analysis.
Scrape one URL · safe
$ npx firecrawl scrape https://example.com Extracts a single page before broader crawling.
Agent usage examples
Codex CLI
Use Firecrawl for a small list of approved URLs, preserve source links, and summarize extracted markdown separately from your conclusions. Safety notes
- Respect robots, rate limits, and site terms before crawling.
- Agents should crawl a small target set first and store source URLs with extracted content.
What agents can use it for
Firecrawl helps agents collect approved web pages as markdown or structured data while preserving source URLs.
Best fit
Use it for research, documentation ingestion, and small controlled crawl jobs.