> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/integrations/catalog/firecrawl.md).

# Firecrawl

Firecrawl turns websites into clean, structured data. Connect to scrape pages, crawl entire sites, map URLs, and search the web from your AI workflows.

* Knowledge base source

### Connectors

Choose the connector that matches your authentication method. The options below use the names shown in StackAI.

| Connector | Authentication |
| --------- | -------------- |
| Firecrawl | API Key        |

#### Firecrawl

Connect to Firecrawl to scrape and extract content from websites.

**Set up in Firecrawl**

1. Sign up or log in at <https://www.firecrawl.dev>.
2. Open the dashboard; your API key (format `fc-...`) is shown on the main screen under API Keys. Copy it (it may only be shown in full once).

**Set up in StackAI**

1. Open **Settings → Connections**, add a connection, and select **Firecrawl**.
2. Enter the credentials and connection details in the fields below.
3. Save the connection and check its connection status. Select this saved connection when configuring an action or feature that uses it.

**Connection fields**

| StackAI field | Required | What to enter                                                                                                                      |
| ------------- | -------- | ---------------------------------------------------------------------------------------------------------------------------------- |
| API Key       | Yes      | Find your API key in your Firecrawl dashboard under API settings. [Provider instructions](https://www.firecrawl.dev/app/api-keys). |

**Provider documentation:** [Setup reference](https://docs.firecrawl.dev/introduction).

#### Verify the connection

Check that the connection is healthy. Then run a read operation against a resource the connected account can access. A successful connection check confirms authentication; it does not guarantee permission for every action.

If access is denied, check the credential or OAuth permissions, the selected account or environment, and access to the specific resource. Update expired credentials or reconnect after permissions change.

### Use an action

1. Add the required **Firecrawl** action to the workflow.
2. Select a connection when the action requests one.
3. Complete the required fields. Use the reference picker when a value comes from another workflow step.
4. Run the workflow and inspect the action’s output. Check the result before using it in a later step.

### Actions

#### Scrape From Url

Scrape a single URL and return its content, including files such as PDFs. Optionally extract structured data by providing a schema or a prompt. Use this for one known page or file.

**Inputs**

| Field        | Type   | Required | Description                                          |
| ------------ | ------ | -------- | ---------------------------------------------------- |
| Request Body | object | No       | Parameters for scraping a single URL with Firecrawl. |

**Outputs**

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

#### Web Scrape

\[Deprecated — use 'Scrape From Url' instead.] Scrape the content of a single web page. 'Scrape From Url' does the same thing plus structured extraction and output-format options.

> **Deprecated:** Use 'Scrape From Url' instead — it scrapes a single URL with the same capability plus structured extraction and output-format options.

**Inputs**

| Field | Type   | Required | Description                                      |
| ----- | ------ | -------- | ------------------------------------------------ |
| URL   | string | Yes      | Enter the URL of the website you want to scrape. |

**Outputs**

| Field   | Type   | Description                                                     |
| ------- | ------ | --------------------------------------------------------------- |
| Title   | string | The title of the scraped webpage.                               |
| Content | string | The main content extracted from the webpage in markdown format. |
| URL     | string | The URL that was scraped.                                       |

#### Batch Scrape

Scrape a list of URLs you provide and return each page's content. Use this when you already have the specific URLs you want — often paired with Map Urls to discover them first.

**Inputs**

| Field        | Type   | Required | Description |
| ------------ | ------ | -------- | ----------- |
| Request Body | object | No       |             |

**Outputs**

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

#### Map Urls

Discover all the URLs on a website without scraping their content. Given a starting URL, this returns a list of links found across the site or section — including pages and files such as PDFs.

**Inputs**

| Field        | Type   | Required | Description |
| ------------ | ------ | -------- | ----------- |
| Request Body | object | No       |             |

**Outputs**

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

#### Search

Search the web for information

**Inputs**

| Field        | Type   | Required | Description                                      |
| ------------ | ------ | -------- | ------------------------------------------------ |
| Request Body | object | No       | Parameters for searching the web with Firecrawl. |

**Outputs**

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

#### Crawl Website

Crawl an entire website starting from a URL. Firecrawl follows links across the site and returns the content of every page it finds (bounded by your page limit and crawl depth). Use this for a whole site or section — for a single known page use Scrape From Url.

**Inputs**

| Field        | Type   | Required | Description |
| ------------ | ------ | -------- | ----------- |
| Request Body | object | No       |             |

**Outputs**

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Important behavior

Actions that create, update, send, or delete data can change the connected service. Review their inputs before running them. A retry can repeat an operation; consider this when configuring retries for actions that change data.

The catalog lists the fields and capabilities available in the supplied provider definition. Availability can also depend on your deployment and organization’s Feature Access settings.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.stackai.com/integrations/catalog/firecrawl.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
