Firecrawl (web scraping)
Firecrawl (web scraping)
Connect Firecrawl to let Agents scrape and extract content from web pages. Firecrawl is available as a built-in Agent tool and as a fetch method on the Fetch URL Flow step.
What is Firecrawl?
Firecrawl is a web scraping service that converts web pages into clean, structured data. It handles JavaScript rendering, anti-bot measures, and data extraction.
Setting up Firecrawl
Firecrawl is available through platform keys, so you can use it without providing your own API key. If you want to use your own Firecrawl account:
- Sign up at firecrawl.dev
- Get your API key from the dashboard
- In Runtype, go to Settings → Integrations
- Find Firecrawl
- Enter your API key
- Click Save Key
Using Firecrawl as a tool
Enable the Firecrawl built-in tool when configuring an Agent. The Agent can then autonomously scrape web pages when needed.
The tool accepts:
- url (required) — The page to scrape
- formats — Output formats:
markdown(default),html,rawHtml,screenshot,links - onlyMainContent — Strip navigation, footers, and ads (default: true)
- waitFor — Milliseconds to wait for dynamic content before scraping
Use cases
- Competitive intelligence: Monitor competitor pricing
- Lead enrichment: Extract company data from websites
- Content aggregation: Collect articles or listings
- Research: Gather data from multiple sources
Next steps
- Massive (web rendering) for an alternative that unblocks difficult sites with residential geotargeting
- Exa (web search) for finding pages to scrape
- What are Agents? to build Agents that use Firecrawl