> ## Documentation Index
> Fetch the complete documentation index at: https://veryfront.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Firecrawl

> Scrape, crawl, map, and search websites into LLM-ready markdown via the Firecrawl API

## At a glance

* **Availability**: Experimental ([how to enable](/cloud/integrations)).
* **Auth**: API key.
* **Connection**: The key comes from `FIRECRAWL_API_KEY`.
* **Docs**: [https://docs.firecrawl.dev/api-reference/introduction](https://docs.firecrawl.dev/api-reference/introduction)

## Credentials

Set these per environment. See [Connect an integration](/cloud/integrations).

| Variable            | Required | Description                                                                          |
| ------------------- | -------- | ------------------------------------------------------------------------------------ |
| `FIRECRAWL_API_KEY` | Yes      | Firecrawl API key (starts with fc-) [Docs](https://docs.firecrawl.dev/introduction). |

## Setup

1. **Create a Firecrawl account**: Go to [https://www.firecrawl.dev](https://www.firecrawl.dev) and sign up - the free plan includes one-time credits for testing.
2. **Get your API key**: Open [https://www.firecrawl.dev/app/api-keys](https://www.firecrawl.dev/app/api-keys) and copy your key (or create a new one per project).
3. **Store the key**: Add it to your .env file as FIRECRAWL\_API\_KEY=fc-...
4. **Verify access**: Run the Scrape Page tool on a public URL. A 401 means the key is invalid; a 402 means you are out of credits.

* All endpoints consume credits per page; crawls multiply cost by the number of pages - set a small 'limit' first
* Start Crawl is asynchronous: poll Get Crawl Status with the returned job ID until status is 'completed'

Provider API reference: [https://docs.firecrawl.dev/api-reference/introduction](https://docs.firecrawl.dev/api-reference/introduction)

## Tools

| Tool             | Access | Description                                                       |
| ---------------- | ------ | ----------------------------------------------------------------- |
| Scrape Page      | Read   | Scrape a single URL into markdown or other formats                |
| Search Web       | Read   | Search the web and optionally scrape the results' content         |
| Map Site         | Read   | Quickly list the URLs discovered on a website                     |
| Start Crawl      | Write  | Start an asynchronous crawl job over a website (returns a job ID) |
| Get Crawl Status | Read   | Get the status and results of a crawl job                         |

## Example prompts

* Scrape a URL I provide with Firecrawl and summarize its content.
* Start a Firecrawl crawl of a website I provide, then check its status and summarize what was found.