---
asIndexPage: true
---

# Firecrawl

import ToolInfo from "@/app/_components/tool-info";
import Badges from "@/app/_components/badges";
import TabbedCodeBlock from "@/app/_components/tabbed-code-block";
import TableOfContents from "@/app/_components/table-of-contents";
import ToolFooter from "@/app/_components/tool-footer";
import { Callout } from "nextra/components";

<ToolInfo
  description="Enable agents to scrape, crawl, and map websites."
  author="Arcade"
  authType="API Key"
  versions={["0.1.0"]}
/>

<Badges repo="arcadeai/arcade_firecrawl" />

The Arcade Firecrawl MCP Server provides a pre-built set of tools for interacting with websites. These tools make it easy to build agents and AI apps that can:

- Scrape web pages
- Crawl websites
- Map website structures
- Retrieve crawl status and data
- Cancel ongoing crawls

## Available Tools

These tools are currently available in the Arcade Firecrawl MCP Sever.

<TableOfContents
  headers={["Tool Name", "Description"]}
  data={[
    [
      "Firecrawl.ScrapeUrl",
      "Scrape a URL and return data in specified formats.",
    ],
    [
      "Firecrawl.CrawlWebsite",
      "Crawl a website and return crawl status and data.",
    ],
    ["Firecrawl.GetCrawlStatus", "Retrieve the status of a crawl job."],
    ["Firecrawl.GetCrawlData", "Retrieve data from a completed crawl job."],
    ["Firecrawl.CancelCrawl", "Cancel an ongoing crawl job."],
    [
      "Firecrawl.MapWebsite",
      "Map a website from a single URL to a map of the entire website.",
    ],
  ]}
/>

<Callout>
  If you need to perform an action that's not listed here, you can [get in touch
  with us](mailto:contact@arcade.dev) to request a new tool, or [create your own
  tools](/guides/create-tools/tool-basics/build-mcp-server).
</Callout>

## Firecrawl.ScrapeUrl

<br />
<TabbedCodeBlock
  tabs={[
    {
      label: "Call the Tool Directly",
      content: {
        Python: [
          "/examples/integrations/resources/integrations/firecrawl/scrape_url_example_call_tool.py",
        ],
        JavaScript: [
          "/examples/integrations/resources/integrations/firecrawl/scrape_url_example_call_tool.js",
        ],
      },
    },
  ]}
/>

Scrape a URL and return data in specified formats.

**Auth:**

- **Environment Variables Required:**
  - `FIRECRAWL_API_KEY`: Your [Firecrawl](https://www.firecrawl.dev/) API key.

**Parameters**

- **`url`** _(string, required)_ The URL to scrape.
- **`formats`** _(enum ([Formats](/resources/integrations/development/firecrawl/reference#formats)), optional)_ The format of the scraped web page. Defaults to `Formats.MARKDOWN`.
- **`only_main_content`** _(bool, optional)_ Only return the main content of the page. Defaults to `True`.
- **`include_tags`** _(list, optional)_ List of tags to include in the output.
- **`exclude_tags`** _(list, optional)_ List of tags to exclude from the output.
- **`wait_for`** _(int, optional)_ Delay in milliseconds before fetching content. Defaults to `10`.
- **`timeout`** _(int, optional)_ Timeout in milliseconds for the request. Defaults to `30000`.

---

## Firecrawl.CrawlWebsite

<br />
<TabbedCodeBlock
  tabs={[
    {
      label: "Call the Tool Directly",
      content: {
        Python: [
          "/examples/integrations/resources/integrations/firecrawl/crawl_website_example_call_tool.py",
        ],
        JavaScript: [
          "/examples/integrations/resources/integrations/firecrawl/crawl_website_example_call_tool.js",
        ],
      },
    },
  ]}
/>

Crawl a website and return crawl status and data.

**Auth:**

- **Environment Variables Required:**
  - `FIRECRAWL_API_KEY`: Your [Firecrawl](https://www.firecrawl.dev/) API key.

**Parameters**

- **`url`** _(string, required)_ The URL to crawl.
- **`exclude_paths`** _(list, optional)_ URL patterns to exclude from the crawl.
- **`include_paths`** _(list, optional)_ URL patterns to include in the crawl.
- **`max_depth`** _(int, required)_ Maximum depth to crawl. Defaults to `2`.
- **`ignore_sitemap`** _(bool, required)_ Ignore the website sitemap. Defaults to `True`.
- **`limit`** _(int, required)_ Limit the number of pages to crawl. Defaults to `10`.
- **`allow_backward_links`** _(bool, required)_ Enable navigation to previously linked pages. Defaults to `False`.
- **`allow_external_links`** _(bool, required)_ Allow following links to external websites. Defaults to `False`.
- **`webhook`** _(string, optional)_ URL to send a POST request when the crawl is started, updated, and completed.
- **`async_crawl`** _(bool, required)_ Run the crawl asynchronously. Defaults to `True`.

---

## Firecrawl.GetCrawlStatus

<br />
<TabbedCodeBlock
  tabs={[
    {
      label: "Call the Tool Directly",
      content: {
        Python: [
          "/examples/integrations/resources/integrations/firecrawl/get_crawl_status_example_call_tool.py",
        ],
        JavaScript: [
          "/examples/integrations/resources/integrations/firecrawl/get_crawl_status_example_call_tool.js",
        ],
      },
    },
  ]}
/>

Retrieve the status of a crawl job.

**Auth:**

- **Environment Variables Required:**
  - `FIRECRAWL_API_KEY`: Your [Firecrawl](https://www.firecrawl.dev/) API key.

**Parameters**

- **`crawl_id`** _(string, required)_ The ID of the crawl job.

---

## Firecrawl.GetCrawlData

<br />
<TabbedCodeBlock
  tabs={[
    {
      label: "Call the Tool Directly",
      content: {
        Python: [
          "/examples/integrations/resources/integrations/firecrawl/get_crawl_data_example_call_tool.py",
        ],
        JavaScript: [
          "/examples/integrations/resources/integrations/firecrawl/get_crawl_data_example_call_tool.js",
        ],
      },
    },
  ]}
/>

Retrieve data from a completed crawl job.

**Auth:**

- **Environment Variables Required:**
  - `FIRECRAWL_API_KEY`: Your [Firecrawl](https://www.firecrawl.dev/) API key.

**Parameters**

- **`crawl_id`** _(string, required)_ The ID of the crawl job.

---

## Firecrawl.CancelCrawl

<br />
<TabbedCodeBlock
  tabs={[
    {
      label: "Call the Tool Directly",
      content: {
        Python: [
          "/examples/integrations/resources/integrations/firecrawl/cancel_crawl_example_call_tool.py",
        ],
        JavaScript: [
          "/examples/integrations/resources/integrations/firecrawl/cancel_crawl_example_call_tool.js",
        ],
      },
    },
  ]}
/>

Cancel an ongoing crawl job.

**Auth:**

- **Environment Variables Required:**
  - `FIRECRAWL_API_KEY`: Your [Firecrawl](https://www.firecrawl.dev/) API key.

**Parameters**

- **`crawl_id`** _(string, required)_ The ID of the asynchronous crawl job to cancel.

---

## Firecrawl.MapWebsite

<br />
<TabbedCodeBlock
  tabs={[
    {
      label: "Call the Tool Directly",
      content: {
        Python: [
          "/examples/integrations/resources/integrations/firecrawl/map_website_example_call_tool.py",
        ],
        JavaScript: [
          "/examples/integrations/resources/integrations/firecrawl/map_website_example_call_tool.js",
        ],
      },
    },
  ]}
/>

Map a website from a single URL to a map of the entire website.

**Auth:**

- **Environment Variables Required:**
  - `FIRECRAWL_API_KEY`: Your [Firecrawl](https://www.firecrawl.dev/) API key.

**Parameters**

- **`url`** _(string, required)_ The base URL to start crawling from.
- **`search`** _(string, optional)_ Search query to use for mapping.
- **`ignore_sitemap`** _(bool, required)_ Ignore the website sitemap. Defaults to `True`.
- **`include_subdomains`** _(bool, required)_ Include subdomains of the website. Defaults to `False`.
- **`limit`** _(int, required)_ Maximum number of links to return. Defaults to `5000`.

## Auth

The Arcade Web MCP Sever uses [Firecrawl](https://www.firecrawl.dev/) to scrape, crawl, and map websites.

**Global Environment Variables:**

- `FIRECRAWL_API_KEY`: Your [Firecrawl](https://www.firecrawl.dev/) API key.

<ToolFooter pipPackageName="arcade_firecrawl" />