How to Use the Apify MCP in CrewAI

Q: Can one CrewAI agent trigger an Apify scrape and another analyze the data?

Yes. You assign runactor to your researcher agent and getdatasetresults to your analyst agent. They coordinate through sequential or hierarchical execution.

Q: How do I limit which CrewAI agents can run Apify scrapers?

Use the advanced setup with MCPServerHTTP and a tool filter. This lets you restrict access so only your designated researcher agent can execute runs.

Deploy a crew of specialized CrewAI agents to scrape the web, analyze datasets, and coordinate research tasks.

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 CrewAI

Create your Vinkius account to connect Apify to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign scraping tasks to specialized CrewAI agents

The `run_actor` tool gives your research agent the power to trigger web scrapers while other agents wait for the results. This separates the heavy lifting of data extraction from the analytical tasks performed by your crew. The researcher agent starts the scrape, while an analyst agent monitors the execution. This division of labor keeps your operations organized and prevents single-agent bottlenecks.

Pass scraped datasets across your agent crew

The `get_dataset_results` tool allows multiple agents to read from the same scraped dataset simultaneously. Your analyst agent reads the raw data, extracts key insights, and passes the refined JSON to your writer agent. Because the data stays in the shared memory space, agents don't need to re-download files. They coordinate via the MCP Server to pull exactly what they need from the storage bucket.

Let agents manage the entire MCP Server pipeline

The `list_actors` and `list_actor_runs` tools give your manager agent the oversight needed to coordinate complex scraping pipelines. The manager checks past runs to ensure the crew doesn't duplicate work or run unnecessary tasks. If a dataset already exists from a recent run, the manager skips the extraction step. The crew goes straight to analysis, saving you API credits and execution time.

Setup guide

Set up Apify MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Apify tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Apify Analyst",
    goal="Access and analyze Apify data via MCP.",
    backstory="Expert analyst with direct Apify access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Apify transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Apify Analyst",
        goal="Access and analyze Apify data via MCP.",
        backstory="Expert analyst with direct Apify access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Apify transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass the MCP Server URL directly into the agent definition using the `mcps` array. CrewAI automatically discovers the tools and makes them available to that specific agent.

Yes. You assign `run_actor` to your researcher agent and `get_dataset_results` to your analyst agent. They coordinate through sequential or hierarchical execution.

Use the advanced setup with `MCPServerHTTP` and a tool filter. This lets you restrict access so only your designated researcher agent can execute runs.

It supports standard HTTP, SSE, and stdio transports. For cloud setups, the Streamable HTTP transport provides the most reliable connection.

All tool executions run inside an isolated, single-use V8 sandbox. Your credentials and extracted payloads are processed in-memory and deleted immediately upon completion, ensuring absolute isolation.

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