How to Use the Browserless MCP in Google ADK

Q: How do I monitor Browserless performance inside Google ADK?

Your agent can run checksystemhealth and getaccountconfig to assess system status. These metrics can be logged directly to Google Cloud Logging.

Q: Is the HTML returned by Browserless clean enough for Google ADK to parse?

The getpagecontent tool returns fully-rendered, raw HTML. Because Gemini has a massive context window, it can digest the entire DOM without pre-processing.

Feed raw web data directly into Google ADK pipelines using headless Chrome rendering.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browserless MCP to Google ADK

Create your Vinkius account to connect Browserless 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 Browserless with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-million token context ingestion for Google ADK

Feed giant chunks of raw web data straight to Gemini. Using `get_page_content`, your Google ADK agent pulls down massive, JS-rendered DOM trees and processes them instantly inside its million-token context window. This MCP Server bypasses typical static scraping hurdles. Because the browser renders the page fully before returning the payload, your enterprise agent receives complete data to write directly into BigQuery.

Visual document processing with Google ADK

Let Gemini analyze complex layouts using its native multimodal capabilities. Your Google ADK agent calls `take_screenshot` to snap a JPEG of any webpage, then passes the image to Vertex AI for visual reasoning. For archiving, the agent relies on `generate_pdf` to build clean documents. These files go straight into your cloud storage buckets for downstream enterprise pipelines.

Custom scraping automation in Google ADK

Execute complex interaction scripts on dynamic web apps using this MCP toolset. The `run_scrape` tool lets your Google ADK agent dispatch custom code to click buttons, fill forms, and extract deep data. To keep cloud costs in check, the agent uses `get_usage_stats` and `list_active_sessions` to balance the active browser load. If concurrency spikes, the agent throttles its own tool calls.

Setup guide

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

You configure the MCP connection parameters in your Google ADK agent setup. The server manages API keys silently, so your LLM never handles raw credentials.

Yes, the agent can write and execute raw Puppeteer scripts using `run_scrape`. Gemini's code-generation abilities write the script, and the browser runs it.

Your agent can run `check_system_health` and `get_account_config` to assess system status. These metrics can be logged directly to Google Cloud Logging.

The `get_page_content` tool returns fully-rendered, raw HTML. Because Gemini has a massive context window, it can digest the entire DOM without pre-processing.

All execution scripts, screenshot images, and PDF binaries are processed in isolated, ephemeral sandboxes. Vinkius guarantees that your proprietary scraping logic and web data never touch persistent disks.

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