Firecrawl

Firecrawl

Agent-callable tools for Firecrawl, the web-data API: turn any URL into clean, LLM-ready Markdown (scrape), read many URLs at once (batchScrape), crawl a whole site (crawl), discover a site's URLs (map), and search the web (search) — with optional page content. It also covers autonomous structured-data extraction (startAgent), a live driven browser (the interact tools), and Firecrawl's research-paper and developer indexes. Wraps the Firecrawl v2 API.

Independent, unofficial connector for Firecrawl. Not affiliated with, endorsed by, or sponsored by Firecrawl. "Firecrawl" is a trademark of its owner, used only to identify the service this connector works with.

When to use this

• Read a page you have the URL for — scrape returns clean Markdown (or HTML, links, a screenshot, or structured JSON). For many URLs use batchScrape; to follow links across a site use crawl.
• Find pages you don't have the URL for — search the web (optionally scraping each result), or map a site to enumerate its URLs.
• Extract structured data — scrape with the json format for a known URL, or startAgent for open-ended, no-URL extraction.
• Search specialist indexes — academic papers (searchPapers / readPaper / findRelatedPapers) and the developer index of GitHub issues/PRs/docs (searchDeveloper).

Setup

This is an agentskills.io skill.

If the connector has not been installed as a skill yet, install it first with npx skills add zapier/connectors --skill firecrawl (or your harness's own skill-install mechanism), then continue here. Installing the skill copies these files, not dependencies. Before running the CLI, a local MCP server, or zapier-sdk auth commands, run npm install --omit=dev here once. Importing the published package as a dependency in your own project instead? That npm install already resolves everything — see references/use-as-sdk.md.

Want the actual repo source instead — to browse references/, run this connector's tests, or hack on it? See README.md for a scoped git clone.

The connector runs on Node.js 22.18+. Pick the reference that matches how you're running it, and load it before doing anything else:

Scripts

All scripts use one connection, firecrawl (a Firecrawl API key). crawl, batchScrape, and startAgent are asynchronous — they return a job id; poll the matching get*Status script until it reports completed. getCreditUsage doubles as the connection test.

Disambiguation & refusals

These jobs are not supported — don't substitute another tool and report success for something you didn't do:

• Parsing a local or uploaded document (PDF/DOCX/PPTX from the user's machine). This connector scrapes URLs; it has no file-upload tool. Ask for a public URL, or say document parsing isn't available here. (scrape reads a PDF at a URL, but cannot accept uploaded bytes.)
• Scheduled / recurring monitoring ("watch this page and alert me"). There is no monitor or trigger tool — this connector is request/response only. Say it's unsupported.
• Anything that changes a website (submit a form to persist data, post content). The interact tools can drive a browser within a session, but this connector is for reading/extracting web data, not acting on third-party accounts.

For the async tools (crawl, batchScrape, startAgent), act on the job id the start tool returns and poll the matching get*Status; never invent a job id. If you've lost one, recover it with getActivity.

Auth

Every shape passes auth as one connection selector, not the secret — a [<resolver>:]<value> string. Every connector accepts zapier:<connection-id> (Zapier-managed auth — routes through Zapier's auth, retries, and governance layer); some also accept one or more direct-token resolvers (naming and count vary per connector) — check this connector's own resolvers rather than assuming. The <resolver>: prefix is optional; a bare value goes to the first resolver that claims it — a UUID-shaped bare value always claims zapier:. Each script declares the connections it needs and the resolvers each accepts. The exact syntax for passing a connection (and how to see this connector's resolver list) differs by shape — see the reference you loaded above.

Checking what's already configured first? Don't dump environment values to do it — env or env | grep <name> prints the value along with the name, leaking a live credential into the transcript if one is set. Check names only (env | cut -d= -f1 | grep -i <name>) or test a known name directly ([ -n "$VAR_NAME" ]).

No connection yet? Pick one — and follow the reference's own flow to obtain it; never just ask the user for a connection id or token as if they already have one memorized:

Output format

Every script returns a { data, meta } envelope:

• data — the script's result (the shape its outputSchema declares; see the reference you loaded above for how to inspect a script's exact schema in your shape).
• meta.outputDataValidation — what validating data did:
  • { skipped: false, droppedPaths: null } — validated, nothing removed.
  • { skipped: false, droppedPaths: [...], instruction } — validated, but those paths were stripped from data: fields the script returned from the API that the outputSchema doesn't declare. If you need them, re-run with output validation skipped.
  • { skipped: true } — validation was bypassed; data is the raw, unchecked script output.

Reading dropped fields / skipOutputDataValidation. To receive the raw, unvalidated result, opt out of output validation (the exact syntax differs by shape — see the reference you loaded above). Input validation is never skipped.

Trimming the result / filterOutputData. To shrink a large result down to the fields you need, pass a jq expression that post-processes data (again, exact syntax per shape). The jq runs against data only, NOT the { data, meta } envelope, so write it rooted at data (run the script's --help — or your shape's equivalent — to see its output schema). The transformed value replaces data, meta is preserved, and the result is NOT re-validated against the output schema.

References

Load the matching reference file before working in that area: