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

# Firecrawl

> Scrape, crawl, search, and extract structured data from the web — plus sandboxed browser automation

# Firecrawl

Shanone's Firecrawl integration gives your agent 22 tools for turning the web into clean, structured data — single-page scraping, full-site crawling, AI-driven extraction, and even a sandboxed browser for interactive pages.

## Getting Started

<Steps>
  <Step title="Get a Firecrawl API key">
    Create an API key from the [Firecrawl dashboard](https://www.firecrawl.dev/app/api-keys).
  </Step>

  <Step title="Add the key in Shanone">
    Open **Integrations** in the Shanone dashboard, select Firecrawl, and paste the API key.
  </Step>

  <Step title="Retry your request">
    Once saved, `shanone_execute_tool` calls for `firecrawl_*` tools will succeed.
  </Step>
</Steps>

## Available Tools

Shanone provides **22 tools** for Firecrawl, organized into these categories:

<AccordionGroup>
  <Accordion title="Scrape & search">
    `firecrawl_scrape`, `firecrawl_search`
  </Accordion>

  <Accordion title="Crawl">
    `firecrawl_crawl`, `firecrawl_check_crawl_status`
  </Accordion>

  <Accordion title="Extract & map">
    `firecrawl_extract`, `firecrawl_map`
  </Accordion>

  <Accordion title="Interact">
    `firecrawl_interact`, `firecrawl_interact_stop`
  </Accordion>

  <Accordion title="Browser sandbox">
    `firecrawl_create_browser`, `firecrawl_execute_browser`, `firecrawl_list_browsers`, `firecrawl_delete_browser`
  </Accordion>

  <Accordion title="Agent">
    `firecrawl_agent`, `firecrawl_get_job_status`
  </Accordion>

  <Accordion title="Monitor (change detection)">
    `firecrawl_monitor_create`, `firecrawl_monitor_list`, `firecrawl_monitor_get`, `firecrawl_monitor_update`, `firecrawl_monitor_delete`, `firecrawl_monitor_run`, `firecrawl_monitor_check`, `firecrawl_monitor_checks`
  </Accordion>
</AccordionGroup>

## Common Use Cases

<CardGroup cols={2}>
  <Card title="Clean Markdown extraction" icon="file-text">
    Scrape a JS-heavy page and get back clean Markdown instead of raw HTML
  </Card>

  <Card title="Site-wide knowledge base ingestion" icon="database">
    Crawl an entire documentation site and feed the resulting pages into a knowledge base
  </Card>

  <Card title="Schema-based data extraction" icon="table">
    Extract structured fields (prices, specs, contact info) from a list of URLs using a JSON schema
  </Card>

  <Card title="Price/content change monitoring" icon="bell">
    Set up a monitor on competitor pages and get notified when pricing or content changes
  </Card>
</CardGroup>

## Troubleshooting

<AccordionGroup>
  <Accordion title="firecrawl_crawl or firecrawl_extract returns a job ID instead of results">
    These are async operations by default — set `wait_for_completion=True`, or poll `firecrawl_check_crawl_status` / `firecrawl_get_job_status` with the returned job ID.
  </Accordion>

  <Accordion title="firecrawl_scrape fails with a rate limit or auth error">
    Check the error message for "rate limit" (back off and retry) vs. "API key" (the connected Firecrawl API key is invalid or expired and needs to be reconnected).
  </Accordion>

  <Accordion title="Need to click a button or fill a form before scraping">
    A plain `firecrawl_scrape` can't interact with the page — first scrape to get a `scrapeId`, then use `firecrawl_interact` with a `prompt` or `code` to perform the interaction, and call `firecrawl_interact_stop` when finished.
  </Accordion>
</AccordionGroup>