How to Use the Applitools MCP in Google ADK

Q: Can my Google ADK agent pull Applitools batch statistics?

Yes, the agent uses getbatchstats to retrieve passed, failed, and unresolved test counts. This lets the Google ADK agent write summary reports directly to your cloud storage.

Q: What happens if my Applitools API key is invalid in Google ADK?

The agent runs validatekey to check the connection. If it fails, the Google ADK framework raises an error, stopping your automated visual testing pipeline before wasting API calls.

Run Applitools visual test analysis inside your Google ADK pipelines using Gemini's massive context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Applitools MCP to Google ADK

Create your Vinkius account to connect Applitools 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 Applitools with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Large-scale batch analysis via Google ADK

Gemini's long-context window handles massive amounts of visual test results easily. Your Google ADK agent calls `list_batches` and imports the visual test states directly into its context. This setup processes hundreds of visual diffs at once. The agent correlates Applitools batch results with your BigQuery deployment logs to pinpoint exactly which commit broke the layout.

Target branch-specific visual reviews

Stop wasting time searching for UI changes on experimental branches. Your agent executes `list_branch_baselines` to fetch the visual states tied to your active Google Cloud build. This MCP Server tool gives your agent the exact visual footprint of a branch. It matches the branch baselines against current test runs to catch layout drift early.

Direct baseline maintenance using this MCP Server

Keeping visual baselines clean is a chore. Your agent handles it by invoking `list_baselines` and using `delete_baseline` when a page layout gets a permanent face-lift. You control which tools the Google ADK agent can access. Restrict tool access in the toolset configuration so the agent only cleans up baselines in designated test environments.

Setup guide

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

Initialize the server transport using StreamableHttpServerParameters with your Vinkius URL. Pass this toolset to your LlmAgent so Gemini can call the visual testing tools.

Yes, the agent uses `get_batch_stats` to retrieve passed, failed, and unresolved test counts. This lets the Google ADK agent write summary reports directly to your cloud storage.

Your baseline configurations and visual test results are kept within your Google Cloud boundary. The MCP Server acts as a secure bridge, ensuring no third party stores your UI layouts.

The agent runs `validate_key` to check the connection. If it fails, the Google ADK framework raises an error, stopping your automated visual testing pipeline before wasting API calls.

Your visual test metadata is processed in memory inside a zero-trust sandbox. Vinkius ensures that visual diffs and test results are never cached or written to persistent disk storage.

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