Apify MCP

When to choose Apify MCP

Connect to Apify MCP

Choose a connection profile below and replace credential placeholders in your own MCP client. The transport describes the MCP connection.

{
  "mcpServers": {
    "apify-http": {
      "url": "https://mcp.apify.com",
      "headers": {
        "Authorization": "Bearer YOUR_APIFY_TOKEN"
      }
    }
  }
}

{
  "mcpServers": {
    "apify-stdio": {
      "command": "npx",
      "args": [
        "-y",
        "@apify/actors-mcp-server"
      ],
      "env": {
        "APIFY_TOKEN": "YOUR_APIFY_TOKEN"
      }
    }
  }
}

Choose an Actor and collect a small dataset

A suggested sequence using the documented tools. Check the connected server's tool schema before making a call.

1. Find and inspect a candidate

   Search for the target and task, then inspect the candidate input schema and pricing. Decide which fields and result limit the job needs.

   Tools: search-actors, fetch-actor-details

   Sources: Official Apify MCP repository, Apify platform and Actor pricing

2. Run with a bounded input

   Submit the documented input for the selected Actor. Retain the returned run and storage identifiers; check status if execution is still underway.

   Tools: call-actor, get-actor-run

   Sources: Apify MCP integration guide, Official Apify MCP repository

3. Retrieve rows deliberately

   Use the returned dataset identifier to fetch a small page of rows, then increase the requested range only if needed. Dataset reads also count toward platform usage.

   Tools: get-dataset-items

   Sources: Official Apify MCP repository, Apify platform and Actor pricing

Selected tools & example tasks

• search-actors

  Find Actors in Apify Store.

  Example task: Choose candidate scrapers.

  Sources: Official Apify MCP repository
• fetch-actor-details

  Read an Actor input schema, description and pricing.

  Example task: Check suitability before a paid run.

  Sources: Official Apify MCP repository
• call-actor

  Start the selected Actor with its documented input.

  Example task: Collect data with a specialized Actor.

  Sources: Official Apify MCP repository
• get-actor-run

  Read a run status and its associated storage identifiers.

  Example task: Check an unfinished run.

  Sources: Official Apify MCP repository
• get-dataset-items

  Read dataset rows with pagination and filtering.

  Example task: Load a bounded sample into the assistant.

  Sources: Official Apify MCP repository

Troubleshoot the connection

Limits & undocumented behavior

• Actor availability and behavior depend on the chosen Actor and server configuration.
• Local stdio lacks hosted output-schema inference.
• These setup details were checked against documentation; no authenticated run was performed.

Sources & review history

This listing is documentation-confirmed. We reviewed the primary sources below; this is not a successful live connection test.

Record updated 2026-09-27. Review due 2026-10-27.

1. Apify MCP integration guideChecked 2026-09-27 · Hosted and local connection options, authentication and client setup.
2. Official Apify MCP repositoryChecked 2026-09-27 · Tool names, run-to-dataset flow, tool selection and hosted/local differences.
3. Apify platform and Actor pricingChecked 2026-09-27 · Account usage, Actor billing models and storage charges.
4. Cursor MCP configurationChecked 2026-09-27 · Remote URL/header and local command configuration formats.
5. Apify published MCP package metadataChecked 2026-09-27 · Current published package requires Node.js 22 or later; MIT license.

Spotted a change? Share the source and the affected setup step in Site Feedback.

Alternatives to Apify MCP

These integrations share documented capabilities with Apify MCP. Compare their setup and product requirements for your task.