How to Use the Olostep MCP in Google ADK

Q: How do I connect Olostep to my Google ADK agent?

Install the package with pip install google-adk. Then, initialize McpToolset using StreamableHttpServerParameters with your Vinkius URL and register the MCP server in your LlmAgent tools list.

Q: Can a Google ADK agent use Olostep to scrape JavaScript-heavy sites?

Yes. When your agent calls scrapeurl, Olostep spins up a headless browser to render dynamic JS before returning clean markdown to your Gemini model.

Q: How do I limit which Olostep tools are exposed to Google ADK?

You can use the optional toolnames filter in your toolset configuration to expose only specific tools like scrapeurl while hiding admin tools.

Feed raw web data directly to your Google ADK pipelines for BigQuery analysis using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Olostep MCP to Google ADK

Create your Vinkius account to connect Olostep to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Olostep with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Enterprise web ingestion for Google ADK

When your Google ADK agent needs to populate a BigQuery dataset with fresh market data, it can invoke `scrape_url` to capture clean page content. The tool handles complex JS rendering automatically, giving your Gemini models clean text to process. To keep cloud costs in check, your agent can call `get_usage` to monitor API credit consumption before initiating large-scale data collection. This ensures your automated data pipelines stay within budget limits.

High-volume batch scraping via MCP Server

For large-scale intelligence gathering, your Google ADK agent can dispatch hundreds of URLs at once using `create_batch`. This shifts the heavy lifting off your local runtime and into Olostep's parallel scraping infrastructure. The agent then tracks these bulk jobs using `list_batches` and retrieves the final structured results with `get_batch_results`. This asynchronous pattern is perfect for long-context Gemini models processing massive document sets.

Dynamic agent selection for web targets

Different target sites require different scraping profiles, which your agent can manage by querying `list_agents` and `get_agent`. Your Gemini-powered agent can inspect these profiles to select the best scraping setup for a specific URL. Before starting any scraping run, the agent can also execute `check_olostep_status` to confirm the target API is online. This simple check prevents your Google Cloud workflows from hanging on broken external connections.

Setup guide

Set up Olostep 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 Olostep 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="Olostep_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Olostep 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 Olostep. 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 Olostep 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 Olostep MCP in Google ADK

Install the package with `pip install google-adk`. Then, initialize `McpToolset` using `StreamableHttpServerParameters` with your Vinkius URL and register the MCP server in your `LlmAgent` tools list.

Yes. When your agent calls `scrape_url`, Olostep spins up a headless browser to render dynamic JS before returning clean markdown to your Gemini model.

You can use the optional `tool_names` filter in your toolset configuration to expose only specific tools like `scrape_url` while hiding admin tools.

Yes, the integration supports both transport types, allowing you to run the server locally via Stdio or host it on Vinkius using the HTTP stream.

Your target URLs and scraped HTML payloads are transmitted over encrypted TLS connections directly to ephemeral execution environments in our Vinkius MCP server. No scraped page data is stored on disk longer than necessary to complete the extraction job.

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