How to Use the Urlbox MCP in Google ADK

Q: How do I get a PNG screenshot using Urlbox and Google ADK?

Use the capturepng tool directly. The agent calls this function, passing the URL it needs to capture. You'll receive the binary image data back in your long-context reasoning flow.

Q: What tools are available for render status checking with Urlbox and Google ADK?

You use getrenderstatus to check background jobs. If you're running a complex workflow, this function confirms if the initial async request successfully kicked off.

Q: Does the MCP Server support listing webhooks for Google ADK?

Yes, calling listwebhooks lets your agent see all currently registered endpoints. This is important because results from an asynchronous render are sent to these defined webhooks.

Q: Is there a way to get account usage stats using Urlbox and Google ADK?

Absolutely. The getcreditusage tool gives your agent precise, up-to-date statistics on how much credit has been consumed by the web rendering service.

Perform complex web captures and rendering tasks using Google ADK within the Gemini ecosystem.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Urlbox MCP to Google ADK

Create your Vinkius account to connect Urlbox 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 Urlbox with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render Specific Content Using MCP Server

The `render_selector` tool lets agents target and capture only a specific element from a page, ignoring the rest of the clutter. You can also run general renders on raw HTML using `render_html`. This precision is critical when you're feeding data into BigQuery. If you need full-page captures, use the synchronous method with `render_sync`, or if it's a large job, kick off an async process via `render_async`.

Manage Credentials and Storage

Agents can check account limits by calling `get_credit_usage`. They also list all available storage buckets using `list_storage_buckets`, letting the agent know where to save extracted data. Furthermore, they can see which webhooks are active with `list_webhooks`. This allows your Google ADK workflow to manage its own dependencies and state before processing.

List Available Network Proxies

Using the `list_proxies` tool, agents get a rundown of available proxy IP ranges. This is necessary for scaling up tasks when your Gemini model needs to scrape high volumes of data. They can also check account status with `get_account_info`. This helps the overall agent system maintain resilience against network restrictions.

Setup guide

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

Use the `capture_png` tool directly. The agent calls this function, passing the URL it needs to capture. You'll receive the binary image data back in your long-context reasoning flow.

You use `get_render_status` to check background jobs. If you're running a complex workflow, this function confirms if the initial async request successfully kicked off.

Yes, calling `list_webhooks` lets your agent see all currently registered endpoints. This is important because results from an asynchronous render are sent to these defined webhooks.

Absolutely. The `get_credit_usage` tool gives your agent precise, up-to-date statistics on how much credit has been consumed by the web rendering service.

The server accesses account profile and usage statistics when you use `get_account_info` or check credits. This is necessary background data that helps your agent plan its execution scope.

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