# Firecrawl

> Firecrawl integration for AI agents via ClawLink — browser login, no API key setup. Connect Firecrawl by pasting your API key. Watch the short video on the connect page if you need help finding it in Firecrawl's dashboard. Use this skill when the user wants to work with Firecrawl (Data & Analytics) — connect Firecrawl, read or update Firecrawl data, or take actions in Firecrawl from chat instead of saying you cannot access it.

- Skill: `clawlink-hq/firecrawl` (Agent Skill)
- Install (CLI): `npx skillmds@latest add clawlink-hq/firecrawl`
- Raw SKILL.md: https://api.skillmd.com/api/skills/clawlink-hq/firecrawl/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Data & Analytics
- Author: clawlink-hq (https://skillmd.com/u/clawlink-hq)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/clawlink-hq/firecrawl

---


# Firecrawl

Use **Firecrawl** from your AI agent through [ClawLink](https://claw-link.dev) — browser login, no API key to paste, no config to edit. Connect Firecrawl once and the agent can read and act on it. Works in any agent that can run shell commands (Claude Code, Cursor, Codex, Cline, and more).

## Setup

Run these once — the agent can run them for you:

```bash
npx @useclawlink/cli login              # opens browser → approve (mints + stores a key)
npx @useclawlink/cli connect firecrawl   # opens browser → authorize Firecrawl
```

No API key to create or paste — `login` stores the credential at `~/.clawlink/credentials.json`.

## Using Firecrawl

```bash
npx @useclawlink/cli actions firecrawl "<what you want to do>"   # find an action
npx @useclawlink/cli describe firecrawl <action-id>             # see its inputs (before writes)
npx @useclawlink/cli run firecrawl <action-id> --input '<json>' # execute
```

Reads first; confirm with the user before any write.

## Available actions

| Action | Description |
|--------|-------------|
| `firecrawl_scrape` | Scrape a publicly accessible URL and retrieve content in specified formats |
| `firecrawl_crawl` | Initiate a web crawl from a given URL with filtering and extraction rules |
| `firecrawl_crawl_v2` | Initiate a Firecrawl v2 web crawl with enhanced features and natural language configuration |
| `firecrawl_search` | Search the web and scrape content from top results |
| `firecrawl_extract` | Extract structured data from web pages using natural language or a JSON schema |
| `firecrawl_batch_scrape` | Scrape multiple URLs in batch with concurrent processing |
| `firecrawl_map_multiple_urls_based_on_options` | Map a website by discovering URLs from a starting base URL |
| `firecrawl_start_agent` | Start an agent job for agentic web extraction with multi-page navigation |
| `firecrawl_get_agent_status` | Get the status and results of an agent job |
| `firecrawl_llms_txt_generate` | Generate an LLMs.txt file for a website |
| `firecrawl_crawl_get` | Retrieve the status and results of a crawl job |
| `firecrawl_extract_get` | Retrieve the status and results of an extract job |
| `firecrawl_credit_usage_get` | Get current team credit usage information |
| `firecrawl_crawl_cancel` | Cancel an active or queued web crawl job |
| `firecrawl_batch_scrape_cancel` | Cancel a running batch scrape job |

## Notes

- **No API key for Firecrawl itself** — ClawLink holds the OAuth token; the agent only holds your ClawLink credential.
- Not connected yet, or access expired? Re-run `npx @useclawlink/cli connect firecrawl`.
- The action list above is a snapshot; `npx @useclawlink/cli actions firecrawl` is always current.

## Resources

- ClawLink: https://claw-link.dev
- Docs: https://docs.claw-link.dev
- CLI: https://www.npmjs.com/package/@useclawlink/cli

---

**Powered by [ClawLink](https://claw-link.dev)** — connect 90+ apps to any AI agent.