How to Use the Browserbase MCP in Google ADK

Q: Can I limit which Browserbase tools my Google ADK agent can access?

Yes, you can pass a toolnames filter when initializing the toolset. This restricts the agent to specific actions like only creating sessions without the ability to list them.

Give your Google ADK agents the power to spin up cloud browsers and fetch live web data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browserbase MCP to Google ADK

Create your Vinkius account to connect Browserbase 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 Browserbase with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run cloud browsers via Google ADK MCP Server

The `create_browser_session` tool launches a headless Chromium instance in a secure cloud environment. It returns a CDP WebSocket connection that your Gemini-powered agents can use with automation libraries. Integrating this with Google Cloud means your agent can fetch live data from the web and feed it directly into BigQuery. You bypass local setup headaches entirely while keeping your execution environment secure.

Track active automation runs

The `get_browser_session` tool gives your agent the ability to check the current status of any active web task. You can verify if a session is still running or if it encountered an error. Monitoring active sessions helps prevent runaway automation costs. This MCP integration lets your agent make smart decisions about when to wait or when to retry a failed web scrape.

Bulk control over your browser fleet

The `list_browser_sessions` tool retrieves all active browser sessions, while `stop_browser_session` kills specific instances immediately. This gives your agent full control over its cloud footprint. Shutting down idle containers saves resources. Your agent can clean up after itself as soon as it extracts the required data from a target site.

Setup guide

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

Use the McpToolset class to point to your Vinkius HTTP endpoint. Pass this toolset into your LlmAgent constructor to expose the browser tools to Gemini.

Yes, you can pass a tool_names filter when initializing the toolset. This restricts the agent to specific actions like only creating sessions without the ability to list them.

Absolutely. The agent can scrape massive web pages using the browser session and feed that volume of text directly into Gemini's million-token context window.

The integration supports both Stdio and HTTP transports. For most production deployments on Google Cloud, the HTTP transport is the most reliable option.

Yes, all CDP commands and session traffic are fully encrypted. Vinkius manages the authentication token securely, and the cloud browser instances run in isolated sandboxes that get wiped clean the moment a session ends.

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