How to Use the Apify MCP in Cursor

Q: How do I add the Apify MCP Server to my Cursor editor?

Create a .cursor/mcp.json file in your project root or global directory. Add the server under the mcpServers key with your Vinkius credentials and restart your editor.

Q: Can the Cursor Agent run Apify scrapers automatically while I code?

Yes, when you use Agent mode, the editor can call runactor to gather live web data and write code that processes it.

Q: What is the best way to pull Apify dataset items into Cursor?

Ask the agent to use getdatasetitems with a specific limit. This lets you inspect a sample of the scraped JSON without overloading your editor's memory.

Q: How do I stop a scraper run from Cursor if it gets stuck?

You can tell the Cursor Agent to call abortrun with the run ID. This halts the scraper immediately on Apify's servers.

Feed live scraped web data from Apify directly into your Cursor editor to build features with real-world context.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Apify MCP to Cursor

Create your Vinkius account to connect Apify to Cursor and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Apify with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Apify actors directly from the Cursor Agent

The `run_actor` tool launches web scrapers in the background while you write code. You feed the agent an actor ID and input parameters, and it triggers the scrape asynchronously, returning a run ID. The Agent then uses `get_run` to check the progress of the scraper without blocking your active coding session. When you need immediate feedback on a quick scrape, `run_actor_sync` blocks execution and returns the finished data block in one go. If a scraper starts eating up too many compute units, your agent can call `abort_run` to kill the process instantly.

Feed raw JSON datasets directly into Cursor files

The `get_dataset_items` tool pulls structured JSON records from your Apify storage directly into your active workspace. Your agent can read this data to generate accurate parsers, database schemas, or frontend components based on actual scraped payloads rather than mock data. To inspect visual assets or configuration files, `get_key_value_store` pulls specific items like screenshots or raw HTML files. This lets your editor analyze the exact output of a scraper run to debug selector issues or extraction errors.

Configure your scraping pipeline via Cursor MCP Server

The `list_actors` tool lists all available scrapers in your Apify account so your agent knows exactly which tools are ready to deploy. You can also monitor your event pipelines using `list_webhooks` to see which external services get pinged when crawls finish. If you're building a dynamic crawler, `push_to_queue` lets you inject new target URLs into an active run on the fly. To prevent unexpected bills, your agent can call `get_account_limits` to verify your remaining compute units before running a massive job.

Setup guide

Set up Apify MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Apify MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Apify transactions." If the MCP tools are loaded correctly, Cursor will call the Apify tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "apify-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Apify. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Apify now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Apify MCP in Cursor

Create a `.cursor/mcp.json` file in your project root or global directory. Add the server under the `mcpServers` key with your Vinkius credentials and restart your editor.

Yes, when you use Agent mode, the editor can call `run_actor` to gather live web data and write code that processes it.

Ask the agent to use `get_dataset_items` with a specific limit. This lets you inspect a sample of the scraped JSON without overloading your editor's memory.

You can tell the Cursor Agent to call `abort_run` with the run ID. This halts the scraper immediately on Apify's servers.

Your API tokens and scraped dataset payloads are protected by the Vinkius zero-trust sandbox. All credentials are encrypted, and the data flows directly to your local editor without being cached or logged externally.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript