> For the complete documentation index, see [llms.txt](https://notara-1.gitbook.io/notara-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://notara-1.gitbook.io/notara-docs/connectors/firecrawl.md).

# Firecrawl

The Firecrawl connector lets the agent scrape, crawl, and monitor web pages, extracting clean markdown content from any public URL.

## What It Enables

| Tool                    | Capability | Description                                                           |
| ----------------------- | ---------- | --------------------------------------------------------------------- |
| `scrape_webpage`        | `read`     | Scrape a URL and return its content as markdown                       |
| `track_webpage_changes` | `read`     | Compare a page against its last scrape and return a diff              |
| `extract_webpage_data`  | `read`     | Extract structured data — headings, links, and metadata — from a page |
| `crawl_website`         | `read`     | Start a multi-page crawl from a root URL; returns a job ID            |
| `check_crawl_status`    | `read`     | Poll a crawl job and return completed pages                           |

## Setup

Firecrawl is a **platform connector** — Notara provides the API key automatically. No credential is required from you.

The connector is available to all workspaces. To use it, enable the **Firecrawl** tile in **Tools** and it will mount for every channel you configure it on.

## Example Prompts

> "Scrape our competitor's pricing page at example.com/pricing and summarize the plans."

> "Check if acme.com/changelog has changed since last week."

> "Crawl docs.example.com up to 20 pages and give me a summary of what's covered."

> "Extract all the headings and links from this blog post: \[URL]."