Skip to main content
Google ADK Integration The Google Agent Development Kit (ADK) is a flexible and modular framework for developing and deploying AI agents. While optimized for Gemini and the Google ecosystem, ADK is model-agnostic, deployment-agnostic, and built for compatibility with other frameworks. This integration shows how to use the Browserbase MCP Server with ADK to build agents that can interact with web pages using natural language commands.

​
Key features

Automated web workflows

Empower your agent to perform multi-step tasks like logging into websites, filling out forms, submitting data, and navigating complex user flows

Intelligent data extraction

Automatically browse to specific pages and extract structured data, text content, or other information for use in your agent’s tasks

Visual monitoring

Capture full-page or element-specific screenshots to visually monitor websites, test UI elements, or feed visual context back to a vision-enabled model

Natural language control

Interact with web pages using natural language commands powered by Stagehand’s AI primitives, making web automation more context-efficient and reliable.

​
Getting started

Quickstart guide

Get started with Google ADK by following the setup guide
Ready to get started? Check out the setup guide for detailed installation instructions.

​
Further reading

Live session view

Inspect a browser while your workflow runs.

Agent Identity

Understand identity and access for browser automation.