View as Markdown
FireCrawl icon

FireCrawl ACTION

Search

Search the web and get full content from results. See the documentation
  • Action
  • Read only
  • API key
  • SDK
  • MCP

IMPLEMENTATION

Call this tool

Connect a user's FireCrawl account once, then configure and run Search 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-search",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    firecrawl: { authProvisionId: "apn_xxxxxxx" },
    query: "Query",
    scrapeOptionFormats: ["Scrape Option Formats"],
  },
})

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.

Search inputs
Property Type Description
query Query string
The query to search for
Required
scrapeOptionFormats Scrape Option Formats string[]
Search with content scraping. You can specify multiple output formats.
Optional
timeBasedSearch Time Based Search string
Filter the results by time
Optional
customTimeout Custom Timeout integer
Set a custom timeout for search operations. E.g. 30000
Optional
maxResults Max Results integer
The maximum number of results to return
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-search
Version
0.0.3
App
FireCrawl
Authentication
API key
Read-only
Yes
Destructive
No
Open world
Yes