Web scraper (Firecrawl) setup guide

Building blocks: send and receive requests, read the web and other everyday tools.

Ways to connect

Company admins connect apps, on the Integrations page in Everdeck: open Web scraper (Firecrawl), choose one of the ways below, follow its steps and fill in its fields. Everdeck checks what you enter before it saves anything, and asks you to confirm it’s you (your second factor) before you type any secret. How connecting works.

Firecrawl API key

API key.

1. Sign up at https://www.firecrawl.dev, open API Keys (https://www.firecrawl.dev/app/api-keys) and copy your key (it starts with fc-) into the form.
2. Optional: open your Firecrawl account settings, go to the Advanced tab and copy the webhook secret into the form, so alerts about watched pages are also checked against Firecrawl's signature.
3. Check your plan's credits. Reading a page costs 1 credit; asking a question about a page or extracting data costs 4 more; web search costs 2 credits per 10 results.
4. Recommended: on the API Keys page, open the key's menu, click Set limit and give it a credit limit per day, week or month, so agents can't spend the whole team balance.

Field	What to enter
API key	A secret: Everdeck saves it encrypted and never shows it again. Where to find it.
Webhook secret (optional)	A secret: Everdeck saves it encrypted and never shows it again. From Firecrawl's account settings, Advanced tab. When set, alerts about watched pages must also carry Firecrawl's signature.

Disconnecting deletes the credentials Everdeck saved, but Everdeck can't revoke them: the key, token or password itself keeps working at Firecrawl until you delete or rotate it there.

What agents can do

An agent uses an action only when its charter grants it, on the agent’s Tools tab, where you choose whether each one runs by itself (Auto), asks first or never runs. Each action has a risk tier: tier 3 actions, which customers or the public see, ask first unless you choose otherwise, and tier 4 actions (money, deleting things, access) always need a person. How tools and tiers work.

Actions marked Reads outside content return things people outside your company may have written. Agents treat what they read as information, never as instructions, and their riskier actions later in the same session need approval.

• Read a web pageTier 0 · ReadReads outside contentweb_scraper_scrape_page

  Fetch a page or PDF and return its main content as Markdown, with its title, final URL and HTTP status. Add summary to formats for a short summary, or links for the page's links. Handles JavaScript-heavy pages; set wait_ms when content appears late. A cached copy up to 2 days old is used unless max_age_ms is lower (0 forces a fresh fetch).

• Ask a question about a pageTier 0 · ReadReads outside contentweb_scraper_ask_page

  Read a page and answer one question about it, for example "What is the refund window?" or "Which plans include SSO?". Returns only the answer, so it suits long pages.

• Extract structured data from a pageTier 0 · ReadReads outside contentweb_scraper_extract_data

  Pull specific facts from a page as JSON, for example a product's name, price, currency and stock status, or a company's contact details. Describe what to extract; add a JSON Schema to fix the result's shape.

• Search the webTier 0 · ReadReads outside contentweb_scraper_search_web

  Search the web (and optionally news or images) and return titles, URLs and descriptions. Use search_and_read when you also need the pages' text.

• Search and read the top resultsTier 0 · ReadReads outside contentweb_scraper_search_and_read

  Search the web and return the top results with each page's main content as Markdown. Costs a page read per result on top of the search, so keep limit small.

• List a website's pagesTier 0 · ReadReads outside contentweb_scraper_map_site

  List the URLs on a website (from its sitemap and links) with titles where known, without reading them. Give search to rank URLs by relevance, for example "pricing" or "blog".

• Crawl a websiteTier 2 · Reversibleweb_scraper_start_crawl

  Start reading many pages of a site in the background (for example a help centre or a competitor's docs). Returns a crawl id; check it with get_crawl. Each page costs a credit, so the limit is capped at 100 pages per crawl. Use include_paths such as ["blog/.*"] to stay focused.

• Check a crawl and read its pagesTier 0 · ReadReads outside contentweb_scraper_get_crawl

  Get a crawl's status (scraping, completed, failed or cancelled), page counts, credits used and the pages read so far as Markdown. Large results arrive in parts of about 10 MB; when next is present, ask for the next page to get the rest.

• Watch pages for changesTier 2 · ReversibleReads outside contentweb_scraper_watch_pages

  Check up to 20 pages on a schedule and start agent work when one changes, appears or disappears. Give a goal (for example "price or plan changes") so only meaningful changes count. Every check costs a credit per page; the result shows the estimated credits per month.

• List watched pagesTier 0 · ReadReads outside contentweb_scraper_list_monitors

  List the page monitors on the Firecrawl account with their schedule, status, pages and estimated monthly credits.

• See what changed in a checkTier 0 · ReadReads outside contentweb_scraper_get_monitor_check

  Read one monitor check: the pages that changed, appeared or disappeared, each with a unified diff and, when a goal is set, whether the change is meaningful and why.

• Pause or resume watchingTier 2 · Reversibleweb_scraper_set_monitor_status

  Pause a page monitor (no more checks or credits) or resume it.

What can start work

These events from Firecrawl can become tasks for your agents through Intake. How Intake works.

A page the agent is watching (watch_pages) changed, appeared or disappeared.

Connect Web scraper (Firecrawl) first. Then, on the Intake page, open Webhooks and sources, find the connection under Connections without an address yet and select Get its URL. Give that address to Firecrawl as the setup steps above describe: Everdeck shows it only once. Then, on the Rules tab, select New rule to say which requests become tasks and who gets them.

Testing, problems and disconnecting

Everdeck checks the connection when you save it. On the connection’s page in Integrations, Test checks it again at any time.

If Firecrawl later refuses the connection, for example because a key was deleted or a sign-in expired, the connection shows Needs attention on the Integrations page and the people who manage connections are told. Agents can’t use it until a company admin fixes it with Edit.

To stop agents using Web scraper (Firecrawl), open the connection and select Disconnect. Agents stop using it at once and its saved credentials are deleted. What else happens depends on how it was connected: each way above says.