How to use Arcadium Data Scrapers MCP Server

Step by step: in the Apify Store, over the API, from JavaScript or Python, in n8n, and from AI agents through MCP or LangChain.

Free actor; you pay Apify platform usage (live Apify price on 2026-11-03).

1. In the Apify Store (no code)

1. Open arcadium/scrapers-mcp and sign in to Apify (a free account works).
2. Fill in the input form. The fields below are the ones the example uses.
3. Set a maximum cost per run in the run options if you want a hard cap.
4. Start the run. Rows appear in the Output tab as they arrive.
5. Export the dataset as JSON, CSV or Excel, or connect an integration.

Example input:

{
  "waitSecs": 150
}

2. Over the Apify API

The synchronous endpoint runs the actor and returns its rows in one call (for runs up to about five minutes; use the asynchronous run endpoint for longer ones).

curl -X POST "https://api.apify.com/v2/acts/arcadium~scrapers-mcp/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"waitSecs":150}'

3. From JavaScript

// npm install apify-client
import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const run = await client.actor('arcadium/scrapers-mcp').call({
  "waitSecs": 150
});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);

4. From Python

# pip install apify-client
import os
from apify_client import ApifyClient

client = ApifyClient(os.environ["APIFY_TOKEN"])
run = client.actor("arcadium/scrapers-mcp").call(run_input={
    "waitSecs": 150,
})
items = client.dataset(run.default_dataset_id).list_items().items  # apify-client 3.x returns a Run object
print(items)

5. In n8n

Paste this node into a workflow (it is a plain HTTP Request node). Create a Header Auth credential with name Authorization and value Bearer <APIFY_TOKEN>; each returned row becomes one item for the next node.

{
  "nodes": [
    {
      "name": "Run arcadium/scrapers-mcp",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4,
      "position": [
        0,
        0
      ],
      "parameters": {
        "method": "POST",
        "url": "https://api.apify.com/v2/acts/arcadium~scrapers-mcp/run-sync-get-dataset-items",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "{\"waitSecs\":150}",
        "options": {
          "timeout": 300000
        }
      }
    }
  ],
  "connections": {}
}

6. From an AI assistant (MCP)

Add Apify’s MCP server to Claude Desktop, Cursor, VS Code or any MCP client, limited to this actor:

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com/?tools=arcadium/scrapers-mcp",
      "headers": {
        "Authorization": "Bearer <APIFY_TOKEN>"
      }
    }
  }
}

More on the MCP page.

7. From LangChain

# pip install langchain-apify   (reads APIFY_API_TOKEN from the environment)
from langchain_apify import ApifyActorsTool

tool = ApifyActorsTool("arcadium/scrapers-mcp")
rows = tool.invoke({"run_input": {
    "waitSecs": 150,
}})
# or give `tool` to an agent: create_react_agent(llm, [tool])

Sample output

Tutorials

• Connect the Arcadium Data scrapers to Claude and Cursor through one MCP endpoint

Schedule it

In Apify Console, create a Task from your input and add a Schedule (for example daily). Each run writes a new dataset; integrations can push the rows to Google Sheets, Slack, a webhook or your database.