How to Use the Apify MCP in AutoGen

Q: How do AutoGen agents collaborate on an Apify run?

One agent starts the scrape with runactor, while another uses getrun to monitor status. A third agent then processes the output from getdatasetitems.

Q: Can an AutoGen agent stop a runaway Apify scraper?

Yes, your monitoring agent can call abortrun if it notices the billing limits are close to being exceeded. This keeps costs under control automatically.

Q: How do I register the Apify MCP Server in AutoGen?

Use the autogen-ext package to load the tools. Pass the server URL to StreamableHttpServerParams and assign the tools to your assistant agent.

Q: Can AutoGen agents dynamically add URLs to an active queue?

Yes, agents use pushtoqueue to feed new URLs into a running queue. This lets them discover and crawl new pages dynamically.

Let your AutoGen agents debate and execute web scraping workflows with this dedicated MCP Server.

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 AutoGen

Create your Vinkius account to connect Apify to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate scraping tasks with an MCP Server

`run_actor` lets your execution agent start scraping jobs while your supervisor agent monitors progress. This separation of duties prevents single-agent bottlenecks during complex web data gathering. While the scrape runs, other agents can plan the next analysis step. You get a parallelized workflow that doesn't stall on slow web pages.

Dynamically expand crawl queues

`push_to_queue` allows your analysis agent to add new URLs to an active run on the fly. As one agent finds interesting links in the scraped data, it tells the scraper to follow them. This creates a smart, feedback-driven crawler. Your agents decide what to scrape next based on what they just read.

Manage webhooks for agent coordination

`list_webhooks` helps your system track event-driven triggers across your scraping fleet. Your agents inspect configured webhooks to align their actions with external system notifications. This ensures your multi-agent team stays in sync with platform events. You don't waste API calls polling for completed runs.

Setup guide

Set up Apify MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Apify tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Apify_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Apify data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Apify_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Apify data")
    print(result.messages[-1].content)

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 AutoGen

One agent starts the scrape with `run_actor`, while another uses `get_run` to monitor status. A third agent then processes the output from `get_dataset_items`.

Yes, your monitoring agent can call `abort_run` if it notices the billing limits are close to being exceeded. This keeps costs under control automatically.

Use the `autogen-ext` package to load the tools. Pass the server URL to `StreamableHttpServerParams` and assign the tools to your assistant agent.

Yes, agents use `push_to_queue` to feed new URLs into a running queue. This lets them discover and crawl new pages dynamically.

Your credentials are encrypted and stored only on Vinkius. The MCP Server executes inside an ephemeral V8 sandbox, ensuring your scraping tokens and JSON datasets remain completely private.

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