Can my AI automatically read the logs of a failed Selenium test?

Yes. When you ask it to investigate a recently failed build, the agent can use `get_build` to find the failed session, and then automatically call `get_session_logs`. It will download the raw textual execution steps directly into the chat and summarize why the UI test failed.

Is there a risk that my AI alters my testing scripts or repository code?

No, this MCP server integrates exclusively with BrowserStack Automate API. It can read statuses, logs, and configurations, and can delete hung sessions or builds, but it has no connection to your actual codebase or git repository.

How can I resolve concurrent session limits preventing my pipeline from advancing?

You can ask your agent to `get_plan` to inspect your parallel boundaries and verify if you are queuing. Then, the agent can look up stalled items via `list_builds` and execute `delete_session` or `delete_build` to manually unblock stuck processes.

BrowserStack MCP Server for Google ADK 10 tools — connect in under 2 minutes

Name: BrowserStack
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 10 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add BrowserStack as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="browserstack_agent",
    instruction=(
        "You help users interact with BrowserStack "
        "using 10 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About BrowserStack MCP Server

Connect your BrowserStack Automate account to any AI agent and take full control of your automated cross-browser testing pipeline through natural conversation.

Google ADK natively supports BrowserStack as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 10 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Project Management — List all test projects and drill down into specific project details
Build Tracking — Surface your recent automation builds, their statuses (running, failed, passed), and duration
Session Deep Dive — Retrieve the granular executions of a specific test session, including OS and browser stats
Log Extraction — Automatically dump and analyze the raw Selenium/Appium logs of a failed session
Quota & Plan — View your current plan's parallel session usage and testing queue length
Environment Specs — List all supported OS/browser combinations required to configure your capabilities

The BrowserStack MCP Server exposes 10 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect BrowserStack to Google ADK via MCP

Follow these steps to integrate the BrowserStack MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 10 tools from BrowserStack via MCP

Why Use Google ADK with the BrowserStack MCP Server

Google ADK provides unique advantages when paired with BrowserStack through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with BrowserStack

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine BrowserStack tools with BigQuery, Vertex AI, and Cloud Functions

BrowserStack + Google ADK Use Cases

Practical scenarios where Google ADK combined with the BrowserStack MCP Server delivers measurable value.

Enterprise data agents: ADK agents query BrowserStack and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine BrowserStack tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query BrowserStack regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including BrowserStack

BrowserStack MCP Tools for Google ADK (10)

These 10 tools become available when you connect BrowserStack to Google ADK via MCP:

delete_build

json`. Delete a BrowserStack build by ID

delete_session

json`. Delete a BrowserStack session by ID

get_build

json`. Returns session details, OS/browser combos, results, and logs. Get all sessions within a BrowserStack automation build

get_plan

json`, including parallel sessions allowed, team parallel sessions used, queued sessions, and plan name. Essential for managing execution concurrency. Get current BrowserStack plan details and parallel session usage

get_project

json`. This includes name, group ID, and recent builds associated with the project. Get full details of a BrowserStack project including linked builds

get_session

json`. Includes name, OS, browser, status, reason, duration, video URL, and log URLs. Get full details of a specific BrowserStack session

get_session_logs

Useful for debugging failed test steps. Get text execution logs of a BrowserStack session

list_browsers

json`. Returns OS names/versions, browser names/versions required for configuring automation desired capabilities. List all supported OS/browser combinations on BrowserStack

list_builds

json`. Returns build names, IDs, statuses (running/done/timeout/failed), durations, and session counts. Useful for tracking test suite execution. List recent builds on BrowserStack Automate

list_projects

json`. Returns project names, IDs, and build counts. Used to organize automation runs. List all projects on BrowserStack Automate

Example Prompts for BrowserStack in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with BrowserStack immediately.

"List my recent automation builds and summarize their outcomes."

"Fetch the logs for the failed session in build e4da3b."

"Check how many parallel sessions our current plan allows."

Troubleshooting BrowserStack MCP Server with Google ADK

Common issues when connecting BrowserStack to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

BrowserStack + Google ADK FAQ

Common questions about integrating BrowserStack MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.