FirecrawlAgent

Firecrawl · Tools and frameworks · json

User-agent: FirecrawlAgent
Disallow: /
robots.txt tokenFirecrawlAgent
User-agent containsFirecrawlAgent
OperatorFirecrawl
CategoryTools and frameworks
robots.txtobeys robots.txt (documented)
Verify byno published verification method

What it is

A hosted scrape-to-markdown service that LLM applications call to read pages. The requester is whoever is building on it, not Firecrawl itself, so volume and intent vary wildly.

What blocking it costs you

Applications built on Firecrawl cannot read your pages. This is increasingly how agents fetch the web, so it is a bigger block than its name suggests.

Full user-agent string

Mozilla/5.0 (compatible; FirecrawlAgent/1.0; +https://firecrawl.dev)

Allow it instead

User-agent: FirecrawlAgent
Allow: /

Operator documentation: https://docs.firecrawl.dev/
Machine copies: json · markdown
Policies that name this crawler: allow-all · maximum-ai-visibility