How to Use the Apify MCP in AutoGen

Q: Can an AutoGen agent decide which Apify actor to run?

Yes. The planning agent calls listactors to view your available scrapers, matches them to the goal, and runs the selected one via runactor.

Q: How do AutoGen agents share Apify dataset results?

One agent retrieves the data using getdatasetresults. It then posts the raw JSON to the group chat, allowing analyst and critic agents to inspect and process the data.

Let your AutoGen agents debate and coordinate complex web scraping tasks using Apify.

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 Scraper Runs Across AutoGen Agents

One AutoGen agent can use our MCP tool `run_actor` to kick off a scraping job, while a supervisor agent monitors its progress with `get_run_details`. This separates the scraping execution from the data validation logic in your conversation. If the validation agent finds issues, it instructs the executor agent to run a different task using `list_actor_tasks`. This multi-agent feedback loop ensures your AutoGen group only parses high-quality web data.

Multi-Agent Data Extraction via MCP Server

Your AutoGen agents can search through active scraping resources using `list_actors`. A planning agent selects the best scraper for the job, while an analyst agent pulls the final results with `get_dataset_results`. This division of labor prevents rate-limiting issues. The planning agent checks `list_actor_runs` to make sure you aren't running duplicate scrapers before starting a new run.

Verify and Clean Scraped Datasets in AutoGen

Once a scraper finishes, your AutoGen analyst agent calls `list_datasets` to locate the target storage. It retrieves the raw payload and passes it to a critic agent to check for formatting errors or missing fields. Because the tools are shared across the AutoGen group, any agent can access the dataset results. This allows for complex collaborative cleaning pipelines before saving the final output.

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

Yes. The planning agent calls `list_actors` to view your available scrapers, matches them to the goal, and runs the selected one via `run_actor`.

One agent retrieves the data using `get_dataset_results`. It then posts the raw JSON to the group chat, allowing analyst and critic agents to inspect and process the data.

Yes. Multiple agents can trigger different scrapers simultaneously using `run_actor`. The server handles concurrent connections seamlessly through Vinkius's hosted infrastructure.

You don't need to pass keys to individual agents. Vinkius manages your Apify API tokens securely, exposing a single endpoint that your AutoGen client connects to via MCP.

Your scraping runs, actor configurations, and dataset contents are highly secure. Vinkius processes all tool calls in isolated, ephemeral V8 runtimes, ensuring your data remains strictly between AutoGen and Apify.

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