How to Use the Apify MCP in Google ADK

Q: How do I register the Apify MCP Server inside a Google ADK agent?

Use McpToolset with your Vinkius HTTP endpoint inside your Python script. Pass the toolset object directly into the tools parameter of your LlmAgent constructor to give Gemini access to the scraping tools.

Q: How does Google ADK handle large dataset payloads from Apify?

The getdatasetitems tool supports pagination via limit and offset parameters. Your agent can fetch items in batches of 1000 to avoid hitting API rate limits or overwhelming the model's input buffer.

Q: Can I track my Apify billing limits through the agent?

Yes, the getaccountlimits tool lets your agent check active compute unit limits and subscription tiers. You can program your agent to halt execution if your Apify account is running low on resources.

Q: How is my scraped Apify data protected when queried by Google ADK?

All data retrieved via getdatasetitems or getkeyvaluestore is transmitted over TLS directly to your Google Cloud environment. Vinkius executes these MCP calls within isolated runner memory, meaning your scraping payloads are processed in memory and never cached or stored on the Vinkius platform.

Trigger Apify scrapers and stream structured datasets directly into Gemini with Google ADK. Built for enterprise data pipelines.

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 Google ADK

Create your Vinkius account to connect Apify to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed scraped datasets into Google ADK agents using MCP

This MCP Server exposes `get_dataset_items` to pull thousands of rows of web data directly into Gemini's million-token context window. Your agent calls `list_actors` to find the right scraper, runs it, and processes the output in a single step. Because Google ADK integrates with Vertex AI, your agent can extract clean structured data and immediately format it for ingestion. You bypass the usual context limitations by letting the model read raw datasets directly from Apify's storage.

Control cloud scrapers inside the Google ADK environment

The `run_actor` and `run_actor_sync` tools give your Gemini-powered agents direct execution power over Apify's cloud-based browser scrapers. If an agent detects a failure or a change in target site layout, it can call `abort_run` to save compute units. This setup lets you build autonomous data pipelines on Google Cloud that react to web changes on the fly. The agent acts as an operator, starting runs and checking status via `get_run` without human intervention.

Queue dynamic URLs using Gemini reasoning

The `push_to_queue` tool allows your agent to dynamically add discovered URLs to an active scraping queue during execution. Your agent can read intermediate results from `get_key_value_store` to decide which links to scrape next. This enables deep, multi-page crawling where the agent decides the path based on live page content. By combining Gemini's reasoning with Apify's queue system, you get a crawler that adapts to complex site architectures.

Setup guide

Set up Apify MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Apify tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Apify_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Apify tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Use `McpToolset` with your Vinkius HTTP endpoint inside your Python script. Pass the toolset object directly into the `tools` parameter of your `LlmAgent` constructor to give Gemini access to the scraping tools.

Yes, your agent can trigger multiple asynchronous runs using `run_actor`. It can then poll the status of each job using `get_run` and process the datasets in parallel as they complete.

The `get_dataset_items` tool supports pagination via limit and offset parameters. Your agent can fetch items in batches of 1000 to avoid hitting API rate limits or overwhelming the model's input buffer.

Yes, the `get_account_limits` tool lets your agent check active compute unit limits and subscription tiers. You can program your agent to halt execution if your Apify account is running low on resources.

All data retrieved via `get_dataset_items` or `get_key_value_store` is transmitted over TLS directly to your Google Cloud environment. Vinkius executes these MCP calls within isolated runner memory, meaning your scraping payloads are processed in memory and never cached or stored on the Vinkius platform.

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