SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Browser tool MCP with Google ADK

Connect Google ADK to Browser tool MCP. Copy highlighted text from this webpage, drag and drop a file to upload section, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Browser tool logoBrowser tool
No Auth

Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow.

5 Tools

Introduction

This guide walks you through connecting Browser tool to Google ADK using the Composio tool router. By the end, you'll have a working Browser tool agent that can run browser tasks, watch them in real time, download task files, and stop running tasks through natural language commands.

This guide will help you understand how to give your Google ADK agent real control over a Browser tool account through Composio's Browser tool MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Browser tool with

Claude CodeCursorChatGPTClaude CoworkAntigravityOpenAI Agents SDKClaude Agent SDKGrok BotMuseCodexGrok BuildVS CodeOpenCodeOpenClawHermesAtomic AgentPiDeepSeek HarnessLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • Get a Browser tool account set up and connected to Composio
  • Install the Google ADK and Composio packages
  • Create a Composio Tool Router session for Browser tool
  • Build an agent that connects to Browser tool through MCP
  • Interact with Browser tool using natural language

What is Google ADK?

Google ADK (Agents Development Kit) is Google's framework for building AI agents powered by Gemini models. It provides tools for creating agents that can use external services through the Model Context Protocol.

Key features include:

  • Gemini Integration: Native support for Google's Gemini models
  • MCP Toolset: Built-in support for Model Context Protocol tools
  • Streamable HTTP: Connect to external services through streamable HTTP
  • CLI and Web UI: Run agents via command line or web interface

What is the Browser tool MCP server, and what's possible with it?

The Browser Tool MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to Browser Tool. It provides structured and secure access to AI-powered browser tasks and sessions, so your agent can automate web interactions, monitor task progress, watch sessions, retrieve generated files, and stop tasks on your behalf.

  • AI-powered browser automation: Have your agent navigate websites, extract data, complete forms, monitor pages, or run automated website tests.
  • Task progress monitoring: Let the agent follow an active browser task until its results are ready.
  • Live session viewing: Direct your agent to provide a live browser session link so you can watch the task in real time.
  • Generated file retrieval: Instruct your agent to retrieve a downloadable file created during a browser task.
  • Task and session control: Have your agent stop a running browser task and end its session when it is no longer needed.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • A Google API key for Gemini models
  • A Composio account and API key
  • Python 3.9 or later installed
  • Basic familiarity with Python
2

Getting API Keys for Google and Composio

Google API Key
  • Go to Google AI Studio and create an API key.
  • Copy the key and keep it safe. You will put this in GOOGLE_API_KEY.
Composio API Key and User ID
  • Log in to the Composio dashboard.
  • Go to Settings → API Keys and copy your Composio API key. Use this for COMPOSIO_API_KEY.
  • Decide on a stable user identifier to scope sessions, often your email or a user ID. Use this for COMPOSIO_USER_ID.
3

Install dependencies

bash
pip install google-adk composio python-dotenv

Inside your virtual environment, install the required packages.

What's happening:

  • google-adk is Google's Agents Development Kit
  • composio connects your agent to Browser tool via MCP
  • python-dotenv loads environment variables
4

Set up ADK project

bash
adk create my_agent

Set up a new Google ADK project.

What's happening:

  • This creates an agent folder with a root agent file and .env file
5

Set environment variables

bash
GOOGLE_API_KEY=your-google-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id-or-email

Save all your credentials in the .env file.

What's happening:

  • GOOGLE_API_KEY authenticates with Google's Gemini models
  • COMPOSIO_API_KEY authenticates with Composio
  • COMPOSIO_USER_ID identifies the user for session management
6

Import modules and validate environment

python
import os
import warnings

from composio import Composio
from dotenv import load_dotenv
from google.adk.agents.llm_agent import Agent
from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset

load_dotenv()

warnings.filterwarnings("ignore", message=".*BaseAuthenticatedTool.*")

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_API_KEY is not set in the environment.")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment.")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment.")
What's happening:
  • os reads environment variables
  • Composio is the main Composio SDK client
  • GoogleProvider declares that you are using Google ADK as the agent runtime
  • Agent is the Google ADK LLM agent class
  • McpToolset lets the ADK agent call MCP tools over HTTP
7

Create Composio client and Tool Router session

python
composio_client = Composio(api_key=COMPOSIO_API_KEY)

composio_session = composio_client.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["browser_tool"],
)

COMPOSIO_MCP_URL = composio_session.mcp.url,
print(f"Composio MCP URL: {COMPOSIO_MCP_URL}")
What's happening:
  • Authenticates to Composio with your API key
  • Declares Google ADK as the provider
  • Spins up a short-lived MCP endpoint for your user and selected toolkit
  • Stores the MCP HTTP URL for the ADK MCP integration
8

Set up the McpToolset and create the Agent

python
composio_toolset = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url=COMPOSIO_MCP_URL,
        headers={"x-api-key": COMPOSIO_API_KEY}
    )
)

root_agent = Agent(
    model="gemini-2.5-flash",
    name="composio_agent",
    description="An agent that uses Composio tools to perform actions.",
    instruction=(
        "You are a helpful assistant connected to Composio. "
        "You have the following tools available: "
        "COMPOSIO_SEARCH_TOOLS, COMPOSIO_MULTI_EXECUTE_TOOL, "
        "COMPOSIO_MANAGE_CONNECTIONS, COMPOSIO_REMOTE_BASH_TOOL, COMPOSIO_REMOTE_WORKBENCH. "
        "Use these tools to help users with Browser tool operations."
    ),
    tools=[composio_toolset],
)

print("\nAgent setup complete. You can now run this agent directly ;)")
What's happening:
  • Connects the ADK agent to the Composio MCP endpoint through McpToolset
  • Uses Gemini as the model powering the agent
  • Lists exact tool names in instruction to reduce misnamed tool calls
9

Run the agent

bash
# Run in CLI mode
adk run my_agent

# Or run in web UI mode
adk web

Execute the agent from the project root. The web command opens a web portal where you can chat with the agent.

What's happening:

  • adk run runs the agent in CLI mode
  • adk web . opens a web UI for interactive testing

Complete Code

Here's the complete code to get you started with Browser tool and Google ADK:

python
import os
import warnings

from composio import Composio
from composio_google import GoogleProvider
from dotenv import load_dotenv
from google.adk.agents.llm_agent import Agent
from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset

load_dotenv()
warnings.filterwarnings("ignore", message=".*BaseAuthenticatedTool.*")

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_API_KEY is not set in the environment.")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment.")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment.")

composio_client = Composio(api_key=COMPOSIO_API_KEY, provider=GoogleProvider())

composio_session = composio_client.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["browser_tool"],
)

COMPOSIO_MCP_URL = composio_session.mcp.url


composio_toolset = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url=COMPOSIO_MCP_URL,
        headers={"x-api-key": COMPOSIO_API_KEY}
    )
)

root_agent = Agent(
    model="gemini-2.5-flash",
    name="composio_agent",
    description="An agent that uses Composio tools to perform actions.",
    instruction=(
        "You are a helpful assistant connected to Composio. "
        "You have the following tools available: "
        "COMPOSIO_SEARCH_TOOLS, COMPOSIO_MULTI_EXECUTE_TOOL, "
        "COMPOSIO_MANAGE_CONNECTIONS, COMPOSIO_REMOTE_BASH_TOOL, COMPOSIO_REMOTE_WORKBENCH. "
        "Use these tools to help users with Browser tool operations."
    ),  
    tools=[composio_toolset],
)

print("\nAgent setup complete. You can now run this agent directly ;)")

Conclusion

You've successfully integrated Browser tool with the Google ADK through Composio's MCP Tool Router. Your agent can now interact with Browser tool using natural language commands.

Key takeaways:

  • The Tool Router approach dynamically routes requests to the appropriate Browser tool tools
  • Environment variables keep your credentials secure and separate from code
  • Clear agent instructions reduce tool calling errors
  • The ADK web UI provides an interactive interface for testing and development

You can extend this setup by adding more toolkits to the toolkits array in your session configuration.

TOOLS

Supported Tools

Every Browser tool action and event your agent gets out of the box.

Run Browser Task

Run an AI-powered browser automation task in a new or existing cloud browser session.

Download Task File

Get a download URL for a file generated by a task.

Get Session Live URL

Get session status and, when available, a live URL for watching a browser session.

Stop Browser Task

Kill a browser task and its session.

Watch Browser Task

Poll a browser task for progress and results, returning on a terminal status or after up to 30 seconds of polling.

FRAMEWORKS

How to build Browser tool MCP Agent with another framework

Claude Code logo

Claude Code

Use Browser tool MCP with Claude Code

Cursor logo

Cursor

Use Browser tool MCP with Cursor

ChatGPT logo

ChatGPT

Use Browser tool MCP with ChatGPT

Claude Cowork logo

Claude Cowork

Use Browser tool MCP with Claude Cowork

Antigravity logo

Antigravity

Use Browser tool MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Browser tool MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Browser tool MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Browser tool MCP with Grok Bot

Muse logo

Muse

Use Browser tool MCP with Muse

Codex logo

Codex

Use Browser tool MCP with Codex

Grok Build logo

Grok Build

Use Browser tool MCP with Grok Build

VS Code logo

VS Code

Use Browser tool MCP with VS Code

OpenCode logo

OpenCode

Use Browser tool MCP with OpenCode

OpenClaw logo

OpenClaw

Use Browser tool MCP with OpenClaw

Hermes logo

Hermes

Use Browser tool MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Browser tool MCP with Atomic Agent

Pi logo

Pi

Use Browser tool MCP with Pi

DeepSeek Harness logo

DeepSeek Harness

Use Browser tool MCP with DeepSeek Harness

LangChain logo

LangChain

Use Browser tool MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Browser tool MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Browser tool MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Browser tool MCP with LlamaIndex

CrewAI logo

CrewAI

Use Browser tool MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Browser tool MCP with Pydantic AI

AutoGen logo

AutoGen

Use Browser tool MCP with AutoGen

FAQ

Frequently asked questions

Start with Browser tool.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Browser tool tool your agent needs.Free to start.

Start building