Control and interact with a live browser session on any scraped page — click buttons, fill forms, navigate flows, and extract data using natural language…
Live browser interaction on scraped pages using natural language prompts or code.
Control interactions via natural language prompts ("click login button", "fill email field") or direct code execution in bash, Python, or Node
Persist browser state across sessions using profiles to maintain authentication, cookies, and localStorage
Supports form filling, button clicks, pagination navigation, infinite scroll handling, and multi-step flow completion
Always requires a prior firecrawl scrape call; scrape ID is saved automatically for subsequent interact commands
Use firecrawl interact stop to free resources when done with a session
firecrawl interact
Interact with scraped pages in a live browser session. Scrape a page first, then use natural language prompts or code to click, fill forms, navigate, and extract data.
When to use
Content requires interaction: clicks, form fills, pagination, login
scrape failed because content is behind JavaScript interaction
You need to navigate a multi-step flow
Last resort in the workflow escalation pattern: search → scrape → map → crawl → interact
Never use interact for web searches — use search instead
Quick start
# 1. Scrape a page (scrape ID is saved automatically)
firecrawl scrape "<url>"don't have the plugin yet? install it then click "run inline in claude" again.