Firecrawl

Web crawling and data extraction with scraping, crawling, mapping, structured extraction, and search

Overview

The Firecrawl server provides tools for web crawling and content extraction. Scrape single pages, crawl entire sites, map URL structures, extract structured data with LLM assistance, and search the web — all with fine-grained control over depth, format, and content filtering.

Add to Civic

Connect Firecrawl at app.civic.com

Available Tools (6)

Tool	Description
firecrawl_scrape	Scrape content from a single URL with advanced options for format, tags, and viewport
firecrawl_crawl	Start a crawl job on a website to extract content from multiple pages
firecrawl_check_crawl_status	Check the status of a running crawl job by ID
firecrawl_map	Map a website to discover all indexed URLs before deciding what to scrape
firecrawl_extract	Extract structured information from web pages using LLM capabilities
firecrawl_search	Search the web and optionally extract content from the results

---

Guardrails

In addition to the 14 universal guardrails, this server has 2 server-specific guardrails across 2 operations.

Both guardrails are token-efficiency response transforms (auto-applied), not security guardrails.

Guardrail	Operation	Timing	Description
Crawl - Retain Markdown and URL Only	firecrawl_crawl	Response	Strips all fields except markdown + url from crawl results — auto-applied
Scrape - Retain Markdown and URL Only	firecrawl_scrape	Response	Strips all fields except markdown + url from scrape results — auto-applied

Configure guardrails via the Civic UI or ask the Configurator Agent: “Add guardrails to my Firecrawl server.”