How to Use the Apify MCP in OpenAI Agents SDK

Q: How do I connect the Apify MCP Server to my OpenAI Agents SDK pipeline?

Install openai-agents via pip and initialize the MCP server using MCPServerStreamableHttp with your Vinkius endpoint. Pass this server instance inside the mcpservers list when instantiating your Agent object. Set cacheToolsList=True to speed up tool discovery during agent startup.

Q: Does the OpenAI Agents SDK support synchronous Apify scraping?

Yes, your agent can call runactorsync to block execution until the scraper finishes. This is ideal for quick scrapes under five minutes where you need the dataset ID immediately. For longer jobs, have your agent use runactor and poll the status with getrun.

Q: How do I monitor my usage costs during large scraping runs?

Have your agent call getaccountlimits to inspect your active compute unit usage and subscription constraints. You can write a system prompt that forces the agent to check these limits before launching heavy actors.

Control Apify scrapers directly from OpenAI Agents SDK. Start runs, manage queues, and fetch datasets with built-in safety guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Apify to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run web scrapers directly from OpenAI Agents SDK

This MCP Server exposes `run_actor` and `run_actor_sync` to connect your OpenAI agents to Apify's library of scrapers, giving your models the ability to pull structured data from any website. Your agent triggers scrapers and grabs the resulting payloads directly. Because OpenAI Agents SDK manages state and agent handoffs, you can have one agent run the scrape and another process the raw text. It keeps your scraping logic isolated from your evaluation logic while passing the run IDs between tasks.

Control active runs and scrape queues dynamically

The `push_to_queue` tool lets your agent feed new URLs to an active scraper as it finds them during execution. If a run goes off the rails or eats too many compute units, the agent calls `abort_run` immediately to stop execution. This gives your OpenAI agents real-time control over long-running jobs instead of just hoping for the best. You get control over your budget and scraping depth by letting the agent monitor the scrape run by run.

Fetch structured JSON datasets for agent training

The `get_dataset_items` tool pulls raw scraped JSON directly into your python agent's execution context. Your agents can query `get_key_value_store` to grab cached run assets like screenshots or HTML dumps. This setup lets you feed clean web data straight into your OpenAI fine-tuning or evaluation loops. You don't need to write custom API wrappers; the agent reads the dataset schema and maps it to its internal memory.

Setup guide

Set up Apify MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Apify tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Apify tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Apify tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Apify Agent",
            instructions="You have access to Apify tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip and initialize the MCP server using `MCPServerStreamableHttp` with your Vinkius endpoint. Pass this server instance inside the `mcp_servers` list when instantiating your `Agent` object. Set `cacheToolsList=True` to speed up tool discovery during agent startup.

Yes, your agent can call `run_actor_sync` to block execution until the scraper finishes. This is ideal for quick scrapes under five minutes where you need the dataset ID immediately. For longer jobs, have your agent use `run_actor` and poll the status with `get_run`.

You control tool access at the agent definition level in Python or by configuring permissions on your Vinkius dashboard. If you only want an agent to read data, you can expose `get_dataset_items` while omitting execution tools like `run_actor`.

Have your agent call `get_account_limits` to inspect your active compute unit usage and subscription constraints. You can write a system prompt that forces the agent to check these limits before launching heavy actors.

Your scraped dataset items and key-value payloads remain on Apify's servers, accessed only when your python code calls `get_dataset_items`. Vinkius executes these MCP calls inside secure, ephemeral V8 isolates, meaning no scraped data is ever written to persistent disk or used to train external models.

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