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
| Capability | Value |
|---|---|
| Provider ID | firecrawl |
| Auth kind | api_key |
| Connect flow | Inline API key or platform credential |
| Actions | Yes |
| Events | No |
| Webhook delivery | No |
| Event samples | No |
| Live status | No |
Connect Firecrawl
| Surface | Support |
|---|---|
| App | Open Govern > Integrations, choose Firecrawl, and paste an API key when the project should use its own quota. |
| CLI | The mobius CLI does not connect Firecrawl integrations yet. Use the app or API. |
| API | Call 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.searchUse 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
- Save extracted content as artifacts.
- Pass results to agent steps.
- Watch data usage from integrations.