How to Use the Hyperbrowser (Web Infra for AI) MCP in Google ADK

Q: How does Gemini handle structured extraction with this MCP Server?

Your agent can call extractdata and pass a target JSON schema. Hyperbrowser handles the extraction on its own infrastructure and returns clean, structured data, saving you millions of Gemini input tokens.

Q: How do I use Hyperbrowser (Web Infra for AI) to monitor active browser sessions in Google ADK?

Call listsessions to get a complete list of your running cloud browser instances. You can also use getsession to check the duration and health of any specific browser before sending your agent to interact with it.

Connect Gemini agents to live cloud browsers using the Google ADK to feed raw web data directly into your enterprise pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hyperbrowser (Web Infra for AI) MCP to Google ADK

Create your Vinkius account to connect Hyperbrowser (Web Infra for AI) 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 Hyperbrowser (Web Infra for AI) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed live web content to Gemini long-context windows

`page_content` fetches the complete, raw HTML of any webpage synchronously. Because Gemini models in the Google ADK handle massive token limits, you can dump entire raw DOM trees straight into the prompt for reasoning. If the target page uses heavy dynamic rendering, `create_session` spins up a remote browser to execute the page JavaScript first. This ensures Gemini reads actual rendered content rather than empty script tags.

Execute client-side JS for Google Cloud workflows

`run_script` runs custom JavaScript inside the remote browser to handle complex page interactions. Your Gemini agent uses this to click deep into multi-page enterprise portals. You can write the output of these browser interactions directly to BigQuery using the ADK's native Google Cloud integrations. The agent coordinates the entire MCP workflow from page load to database insert.

Scale enterprise web scraping with Google ADK

`start_scrape` initiates asynchronous web scraping jobs across dozens of target URLs simultaneously. This tool prevents your main enterprise execution loops from timing out on slow websites. Your agent polls `get_scrape_job` to retrieve the completed HTML payloads as they finish. From there, you can pipe the structured results into Vertex AI for downstream embedding generation.

Setup guide

Set up Hyperbrowser (Web Infra for AI) 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 Hyperbrowser (Web Infra for AI) 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="Hyperbrowser (Web Infra for AI)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Hyperbrowser (Web Infra for AI) 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 Hyperbrowser. 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 Hyperbrowser (Web Infra for AI) 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 Hyperbrowser (Web Infra for AI) MCP in Google ADK

Use McpToolset from the google-adk package and pass your Vinkius HTTP URL to StreamableHttpServerParameters. Then add this toolset to your LlmAgent tools configuration to expose the MCP tools to Gemini.

Yes, the McpToolset class allows you to pass an optional tool_names list filter. This lets you limit the agent to safe tools like `page_content` and block state-modifying actions like `stop_session`.

Your agent can call `extract_data` and pass a target JSON schema. Hyperbrowser handles the extraction on its own infrastructure and returns clean, structured data, saving you millions of Gemini input tokens.

Call `list_sessions` to get a complete list of your running cloud browser instances. You can also use `get_session` to check the duration and health of any specific browser before sending your agent to interact with it.

Raw HTML payloads and active session metadata are processed entirely in memory within ephemeral cloud sandboxes. No persistent storage is used, and Vinkius securely manages your endpoint token to prevent unauthorized access to your browser sessions.

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