Firecrawl
Read any web page, including the ones that fight back.
Firecrawl is a data and sourcing tool, and one of the 52 tools hyreflow connects to Claude, ChatGPT and other AI assistants. Through hyreflow, an AI agent can run 6 actions, all of which look something up. Paid Firecrawl actions cost 0.1 credits per result or per request, from your hyreflow credit balance, so you need no Firecrawl account, though you can connect your own key.
Firecrawl renders a page the way a browser does, so it works on sites that return nothing useful to a plain fetch. It reads one page, maps every URL on a site, or crawls the lot, and gives back clean text the agent can reason over.
Firecrawl is the reader. Other tools find the URL; Firecrawl turns it into something worth reading.
What can you ask Claude or ChatGPT to do with Firecrawl?
With hyreflow connected, you ask for the outcome in plain language and the assistant runs Firecrawl for you. For example:
- “Read this careers page url and list every open role”
- “Map this company's site, pull the team page, and match the names in Apollo”
- “Pull the text of these 30 articles and have hyreflow Agent score them against my ICP”
- “Follow the links from Layoff Signal and get me the actual article bodies”
Which tools work well with Firecrawl?
In a hyreflow run, Firecrawl is most often paired with Layoff Signal, hyreflow Agent, Exa and Apollo.
- Layoff Signal
resolve a news link and read the article behind it
- hyreflow Agent
turn scraped pages into structured judgements
- Exa
search by meaning first, then read the winners
- Apollo
match scraped names to real profiles
Which Firecrawl actions can an AI agent run through hyreflow?
Through hyreflow, an AI agent can run 6 Firecrawl actions, all of which look something up. Paid Firecrawl actions cost 0.1 credits per result or per request, from your hyreflow credit balance, so you need no Firecrawl account, though you can connect your own key.
| Firecrawl action | What it does | Cost through hyreflow |
|---|---|---|
| Scrape | Looks something up | 0.1 credits per request |
| Search | Looks something up | 0.1 credits per result |
| Start crawl | Looks something up | 0.1 credits per page |
| Extract | Looks something up | free |
| Map | Looks something up | 0.1 credits per request |
| Get crawl | Looks something up | free |
One credit is priced on the pricing page. The full price list for every tool is in the pricing tables.
Which hyreflow skills use Firecrawl?
20 hyreflow skills call Firecrawl as part of the run. A skill is a whole pipeline your agent already knows, end to end.
Source engineers on proof of work instead of job titles
use whenyou are filling a developer role and the profiles all claim the same stack
Turn a company's public team page into a qualified candidate list
use whena company's own team page already lists the people you want, and the databases hardly know the firm exists
Turn a conference speaker list into candidates worth approaching
use whenan industry event has published its speakers and the people on stage look like the hire your client wants
Build the target account list for a recruitment desk
use whenyou are opening a new market or a new desk and need to know which companies are even worth calling
Find more companies like your best clients
use whenyou can name the five to ten clients you would clone if you could, and you want the companies that look like them
Find the hiring manager behind a job ad that names nobody
use whenyou have a job ad, or a handful of them, and none of them names anybody you can write to
How does an AI agent know how to use Firecrawl?
hyreflow ships a written playbook for Firecrawl, and the agent loads it before the first call. Auth, rate limits, what each call costs, which actions need your approval, and the mistakes worth avoiding. It is the difference between an agent that knows the tool and one that guesses at it.
Read the Firecrawl docs →Show the raw playbookwritten for the agent
HOW in lib/firecrawl.py. Also the project's tier-3 doc scraper (see reference/docs/*/scrape_docs.py).
Auth & config
- Base URL:
https://api.firecrawl.dev· Auth:Authorization: Bearer <key>(envFIRECRAWL_API_KEY; never hardcode).
Operations
scrape(url, formats=['markdown'])— render & scrape one page (sync).map(url, search=, limit=)— list all URLs on a site (use to discover endpoint/doc pages → then scrape each). This is the tier-3 doc-pipeline entrypoint.search(query, scrape_options=)— web search + optional scrape of results.extract(urls, prompt=/schema=)— LLM structured extraction.start_crawl(url)→{id};get_crawl(id)— async multi-page crawl.
Cost note
Billed per scrape/crawl/extract. Read-only (no outreach side-effects) — spend awareness only.
Handoff
The fallback doc/data scraper: when a tool's docs are a JS SPA (tier 3), map → scrape each page → cache → build adapter (the exact pattern used for Recruit CRM).
Callable surface — lib/firecrawl.py
Import: from lib.firecrawl import Firecrawl → instantiate Firecrawl() (reads key from env). Base: https://api.firecrawl.dev. Generic passthrough: request(method, path, *, params, json).
extract(urls: list[str], *, prompt: str | None = None, schema: dict | None = None, **opts) -> dict— POST /v2/extract — LLM structured extraction across URLs.get_crawl(crawl_id: str) -> dict— GET /v2/crawl/{id} — poll crawl status + collected pages.get_credit_usage() -> dict— GET /v2/team/credit-usage — remaining team credits + billing period. Free, no args — the BYOK key-verification probe.map(url: str, *, search: str | None = None, limit: int | None = None, **opts) -> dict— POST /v2/map — discover all URLs on a site (sitemap). Use to find endpoint/doc pages.scrape(url: str, *, formats: list[str] | None = None, only_main_content: bool = True, **opts) -> dict— POST /v2/scrape — render & scrape one URL. formats e.g. ['markdown','html','links'].search(query: str, *, limit: int | None = None, scrape_options: dict | None = None, **opts) -> dict— POST /v2/search — web search, optionally scraping each result.start_crawl(url: str, **opts) -> dict— POST /v2/crawl — start an async multi-page crawl. Returns {id}.
Questions about Firecrawl and hyreflow
Can I use Firecrawl inside Claude or ChatGPT?
Yes. hyreflow is a connector for Claude, ChatGPT and other AI assistants. Once hyreflow is connected, you ask for the outcome in plain language and the assistant calls Firecrawl for you. hyreflow exposes 6 Firecrawl actions this way.
Do I need my own Firecrawl account to use it with hyreflow?
No. hyreflow holds the Firecrawl account and bills each action from your hyreflow credits. If you already pay for Firecrawl, you can connect your own key instead, and hyreflow then charges no credits for those calls.
What does Firecrawl cost through hyreflow?
Paid Firecrawl actions cost 0.1 credits per result or per request, from your hyreflow credit balance, so you need no Firecrawl account, though you can connect your own key. 2 actions are free. hyreflow can show the cost of a paid action before it runs.
How do I connect Firecrawl to an AI agent over MCP?
Add the hyreflow MCP server to your assistant and sign in. hyreflow calls the Firecrawl API directly and exposes its actions as tools the assistant can run, so there is no separate Firecrawl server to install.
Put Firecrawl to work from one prompt
Connect hyreflow to Claude or ChatGPT and ask for the outcome. It reads the playbook above before it makes a single call.