Power AI agents with clean web data

The API to search, scrape, and interact with the web at scale. It's also open source.

Start scraping today

The infrastructure layer that helps AI find, read, and act on the live web.

Main Features

  • Search: Search the web and get full content from results.
  • Scrape: Get llm-ready data from websites. Markdown, JSON, screenshot, etc.
  • Interact: Scrape a page, then interact with it using AI prompts or code.

Code Examples

Python Example

# pip install firecrawl-py
from firecrawl import Firecrawl

app = Firecrawl(api_key="fc-YOUR_API_KEY")

# Scrape a website:
app.scrape('firecrawl.dev')

JSON Example

[
  {
    "url": "https://?999!-e.*zz",
    "markdown": "! A--!inz --0r-09*9*",
    "json": { "title": "-9ad?", "docs": "..." },
    "screenshot": "--aZ0:-Z-AAm=-9zc-m/!eZz.png"
  }
]

Easily connect with your AI agents

Connect Firecrawl to any AI agent or MCP client in minutes.
One command: 

npx -y firecrawl-cli@latest init --all --browser

Quick config: 

{
  "mcpServers": {
    "firecrawl-mcp": {
      "command": "npx",
      "args": ["-y", "firecrawl-mcp"],
      "env": {
        "FIRECRAWL_API_KEY": "fc-YOUR_API_KEY"
      }
    }
  }
}

FAQ

What is Firecrawl?

Firecrawl helps AI systems search, scrape, and interact with the web. One API to turn websites into clean, LLM-ready data. Ideal for AI companies looking to empower their LLM applications with web data.

What can I build with Firecrawl?

Teams use Firecrawl for deep research agents, RAG pipelines, lead enrichment, competitive intelligence, content generation, price monitoring, and more.

Is Firecrawl open-source?

Yes. Firecrawl is the largest open source repo in the space with over 100,000 GitHub stars. We're building this in the open, and community adoption reflects that. You can check out the repository on GitHub.

How does /scrape work?

Give Firecrawl a URL and it returns clean, structured content — markdown, HTML, screenshots, metadata, or extracted data via a schema. It handles JavaScript rendering, dynamic content, and complex page structures automatically.

What formats can Firecrawl convert web data into?

Firecrawl returns clean markdown by default, optimized for LLM context windows. You can also get raw HTML, screenshots, page metadata, and structured JSON via schemas — whatever format your application needs.

Does Firecrawl handle JavaScript-rendered pages?

Yes. Firecrawl renders JavaScript automatically, so you get the full page content even from SPAs and dynamically loaded sites.

Is Firecrawl suitable for large-scale projects?

Absolutely. Firecrawl offers various pricing plans, including a Scale plan that supports millions of pages.