Webscrape AI ACTION
Scrape Website
Scrape the provided URL and store the results in the system. See the documentation
- Action
- Writes data
- API key
- SDK
- MCP
IMPLEMENTATION
Call this tool
Connect a user's Webscrape AI account once, then configure and run Scrape Website 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: "webscrape_ai-scrape-website",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
webscrape_ai: { authProvisionId: "apn_xxxxxxx" },
url: "URL",
command: "Command",
},
})
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": "webscrape_ai-scrape-website",
"configured_props": {
"webscrape_ai": { "authProvisionId": "apn_xxxxxxx" },
"url": "URL",
"command": "Command"
}
}'// 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": "webscrape_ai",
},
},
},
)
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: "webscrape_ai-scrape-website",
arguments: {
url: "URL",
command: "Command",
},
})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 of the website to scrape Required |
command Command | string | The data you want to extract. E.g. I want to extract all the news details Required |
schema Schema | string | Schema representing the fields you want to scrape. E.g. {"author":"string","comments_count":"integer","points":"integer","posted_time":"string","title":"string","url":"url"} Required |
pages Pages | integer | Number of pages to scrape. Default value is 1. Optional |
headers Headers | string | List of headers in key-value pairs. i.e Accept: application/json Optional |
instructions Instructions | string | List of JavaScript instructions that you want to execute, like clicking a specific button, waiting for a specific code block to appear, etc. Example: {"click": "#button_id"}. See the documentation for more information. 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
- webscrape_ai-scrape-website
- Version
- 0.0.3
- App
- Webscrape AI
- Authentication
- API key
- Read-only
- No
- Destructive
- No
- Open world
- Yes
- Source
- View on GitHub ↗