Skip to main content

Firecrawl

Web scraping and crawling API that turns a URL into clean markdown an AI model can read. Agents use it to fetch pages without each one carrying its own browser automation.

Containers

ContainerRole
firecrawlREST API and job harness (port 3002)
firecrawl-mcpMCP server — streamable HTTP at http://firecrawl-mcp:3003/mcp
firecrawl-playwrightHeadless browser microservice (internal)
firecrawl-redisRate limiting and job-state cache
firecrawl-rabbitmqCrawl job queue
firecrawl-postgresCrawl results and job history

Access

  • Containers: http://firecrawl:3002 on the exist network
  • Browser: https://firecrawl.EXIST_DOMAIN
  • Agents: point an MCP client at http://firecrawl-mcp:3003/mcp

Enable

EXIST_IS_AI_FIRECRAWL=true

Then ./existential.sh && docker compose up -d from the repo root.

Notes

Its Postgres volume is volumes/firecrawl_postgres_data, declared db: true — local only, never NFS. Scraped content is a cache: if you lose it, re-crawl.