Data and research

Firecrawl

A Firecrawl integration connects Firecrawl to Mobius. Runs can use it to scrape URLs, search the web, and parse files into structured content.

Use Firecrawl when a run needs fresh web content or document extraction before an agent step reasons over the result.

Capability map

CapabilityValue
Provider IDfirecrawl
Auth kindapi_key
Connect flowInline API key or platform credential
ActionsYes
EventsNo
Webhook deliveryNo
Event samplesNo
Live statusNo

Connect Firecrawl

SurfaceSupport
AppOpen Govern > Integrations, choose Firecrawl, and paste an API key when the project should use its own quota.
CLIThe mobius CLI does not connect Firecrawl integrations yet. Use the app or API.
APICall POST /v1/projects/{project}/integrations/providers/firecrawl/connect with the Firecrawl credential body from the API reference.

If the catalog marks Firecrawl ready through a platform credential, the action can run without a project-local key. Connect your own key when usage should be billed to your Firecrawl account.

Actions

firecrawl.parse
firecrawl.scrape
firecrawl.search

Use firecrawl.scrape for a known URL, firecrawl.search for discovery, and firecrawl.parse when the input is a file or document. Save large outputs as artifacts when later steps need to inspect them.

By default firecrawl.search returns only result metadata (title, URL, and description). It does not fetch page content. Let the agent decide which results are worth reading and call firecrawl.scrape on those URLs. To pull page content inline with the search instead, pass scrapeOptions (for example { "formats": [{ "type": "markdown" }] }) on the search action.

Events

Firecrawl does not register source events.

Next