FireCrawl ACTION
Scrape Page
Scrapes a URL and returns content from that page. 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 Scrape Page 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-scrape-page",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
firecrawl: { authProvisionId: "apn_xxxxxxx" },
url: "URL",
formats: ["Formats"],
},
})
console.log(result)curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
-H "Content-Type: application/json" \
-H "X-PD-Environment: production" \
-H "Authorization: Bearer {access_token}" \
-d '{
"external_user_id": "{external_user_id}",
"id": "firecrawl-scrape-page",
"configured_props": {
"firecrawl": { "authProvisionId": "apn_xxxxxxx" },
"url": "URL",
"formats": ["Formats"]
}
}'// accessToken: mint a short-lived token with the Connect SDK — see the MCP guide
const transport = new StreamableHTTPClientTransport(
new URL("https://remote.mcp.pipedream.net/v3"),
{
requestInit: {
headers: {
Authorization: `Bearer ${accessToken}`,
"x-pd-project-id": "{project_id}",
"x-pd-environment": "production",
"x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
"x-pd-app-slug": "firecrawl",
},
},
},
)
const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)
const { tools } = await mcp.listTools()
// listTools() hands your model this tool's input schema, so it can
// fill the arguments itself:
const result = await mcp.callTool({
name: "firecrawl-scrape-page",
arguments: {
url: "URL",
formats: ["Formats"],
},
})SCHEMA
Inputs
Pipedream supplies the connected account. Your application provides the operation-specific values below. Dynamic inputs are resolved against that user's account.
| Property | Type | Description |
|---|---|---|
url URL | string | The URL to scrape Required |
formats Formats | string[] | Formats to include in the output Optional |
onlyMainContent Only Main Content | boolean | Only return the main content of the page, excluding headers, navs, footers, etc. Optional |
includeTags Include Tags | string[] | Tags to include in the output Optional |
excludeTags Exclude Tags | string[] | Tags to exclude from the output Optional |
headers Headers | object | Headers to send with the request. Can be used to send cookies, user-agent, etc. Optional |
waitFor Wait For | integer | Specify a delay in milliseconds before fetching the content, allowing the page sufficient time to load. Optional |
mobile Mobile | boolean | Set to true to emulate scraping from a mobile device. Useful for testing responsive pages and taking mobile screenshots Optional |
timeout Timeout | integer | Timeout in milliseconds for the request Optional |
additionalOptions Additional Options | object | Additional parameters to send in the request. See the documentation for available parameters. Values will be parsed as JSON where applicable. 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-scrape-page
- Version
- 1.0.4
- App
- FireCrawl
- Authentication
- API key
- Read-only
- No
- Destructive
- No
- Open world
- Yes
- Source
- View on GitHub ↗