How to Use the Browserless (Playwright Cloud) MCP in Google ADK

Q: How do I initialize Browserless (Playwright Cloud) in a Google ADK project?

Use the McpToolset class and point it to your Vinkius MCP endpoint. Pass this toolset into your LlmAgent tools array, and your Gemini models will immediately start using the browser tools.

Q: Can I restrict Google ADK to only use specific tools from Browserless (Playwright Cloud)?

Yes, you can use the optional tool names filter in the McpToolset configuration. This lets you restrict your agent to safe tools like getscreenshot while blocking execution tools like runcustomfunction.

Q: How does this server handle single-page applications?

It handles them easily. Your agent can use scrapewithwait to pause execution until a specific DOM element appears, ensuring that dynamically rendered content is fully loaded before extraction.

Give your Google ADK enterprise agents direct access to raw web data with a cloud-managed Playwright MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browserless (Playwright Cloud) MCP to Google ADK

Create your Vinkius account to connect Browserless (Playwright Cloud) 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 (Playwright Cloud) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deep web scraping for Google ADK long-context agents

Gemini models love massive contexts, but you need clean data to fill them. This MCP Server lets your agent pull down massive pages using `get_html_content` or isolate specific sections with `scrape_elements` without blowing up your token budget. By filtering out the noise before feeding the data into Google ADK, your agent processes complex documents faster. It keeps your Vertex pipelines focused on reasoning rather than parsing junk markup.

Execute complex DOM interactions on Google Cloud

Enterprise web portals often hide data behind multi-step login forms or dynamic menus. Your agent can run `scrape_with_js` or `scrape_with_wait` to wait for specific CSS selectors to load before grabbing the data. This allows your Google ADK agent to interact with modern web apps just like a human operator would. It clicks buttons, waits for AJAX calls to finish, and extracts the exact content needed for downstream BigQuery analysis.

Evade bot detection natively using this MCP Server

Many target sites block standard headless scrapers instantly. By calling `scrape_with_stealth`, your Google ADK agent uses advanced browser-fingerprint spoofing to mimic a real human visitor. If a site requires specific request headers or custom endpoints, the agent can use `send_custom_payload` to talk directly to the Browserless API. This ensures your data ingestion pipelines never stall due to sudden IP bans or CAPTCHAs.

Setup guide

Set up Browserless (Playwright Cloud) 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 (Playwright Cloud) 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 (Playwright Cloud)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Browserless (Playwright Cloud) 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 Playwright Cloud. 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 (Playwright Cloud) 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 (Playwright Cloud) MCP in Google ADK

Use the `McpToolset` class and point it to your Vinkius MCP endpoint. Pass this toolset into your `LlmAgent` tools array, and your Gemini models will immediately start using the browser tools.

Yes, you can use the optional tool names filter in the `McpToolset` configuration. This lets you restrict your agent to safe tools like `get_screenshot` while blocking execution tools like `run_custom_function`.

Yes, since the browser runs are offloaded to Vinkius cloud infrastructure, your Google ADK agent can trigger multiple scraping tasks concurrently without exhausting your local CPU or memory.

It handles them easily. Your agent can use `scrape_with_wait` to pause execution until a specific DOM element appears, ensuring that dynamically rendered content is fully loaded before extraction.

Every browser session runs in an isolated, short-lived sandbox. The HTML, PDFs, and screenshots generated during execution are streamed directly to your Google ADK agent and never persist on our servers once the connection closes.

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