View as Markdown
FireCrawl icon

FireCrawl ACTION

Extract Data

Extract structured data from one or multiple URLs. See the documentation
  • Action
  • Writes data
  • API key
  • SDK
  • MCP

IMPLEMENTATION

Call this tool

Connect a user's FireCrawl account once, then configure and run Extract Data from your backend or agent.

import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "firecrawl-extract-data",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    firecrawl: { authProvisionId: "apn_xxxxxxx" },
    urls: ["URLs"],
    prompt: "Prompt",
  },
})

console.log(result)

SCHEMA

Inputs

Pipedream supplies the connected account. Your application provides the operation-specific values below. Dynamic inputs are resolved against that user's account.

Extract Data inputs
Property Type Description
urls URLs string[]
An array of one or more URLs. Supports wildcards (/*) for broader crawling.
Required
prompt Prompt string
(Optional unless no schema): A natural language prompt describing the data you want or specifying how you want that data structured.
Optional
schema Schema object
(Optional unless no prompt): A more rigid structure if you already know the JSON layout.
Optional
enableWebSearch Enable Web Search boolean
When true, the extraction will use web search to find additional data
Optional
ignoreSitemap Ignore Sitemap boolean
When true, sitemap.xml files will be ignored during website scanning
Optional
includeSubdomains Include Subdomains boolean
When true, subdomains of the provided URLs will also be scanned
Optional
showSources Show Sources boolean
When true, the sources used to extract the data will be included in the response
Optional
waitForCompletion Wait For Completion boolean
Set to true to poll the API in 3-second intervals until the job is completed
Optional

REFERENCE

Tool details

Behavior hints are published with the component in the Pipedream registry and surface as MCP tool annotations, so an agent can reason about a tool before it calls it.

Registry key
firecrawl-extract-data
Version
0.0.5
App
FireCrawl
Authentication
API key
Read-only
No
Destructive
No
Open world
Yes