Can my AI agent resolve a test failure on its own?

No. The MCP server is designed for pulling state data—it retrieves batches, session diff links, and match levels so you can review them locally. Approving a new baseline or resolving a mismatch still requires human intervention within the Applitools Eyes dashboard to maintain absolute testing safety.

Can I use the agent to delete old UI snapshots?

Yes. If your UI has undergone major structural changes and old baselines are causing false positives, you can authorize the agent to execute the `delete_baseline` tool. Provide the exact baseline ID to instantly discard the legacy screenshot from your workspace.

How fast can I summarize test errors after my CI/CD action triggers?

Almost instantly. Rather than scrolling through dozens of Applitools logs, ask your agent to 'Get batch stats for ID 123'. It will immediately return the aggregation of Passed, Failed, and Unresolved runs, saving you countless minutes of digging.

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

Name: Applitools
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 Applitools 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="applitools_agent",
    instruction=(
        "You help users interact with Applitools "
        "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 Applitools MCP Server

Connect your Applitools Eyes testing suite to your AI agent and manage your entire visual regression pipeline without opening the dashboard. Allow your agent to spot UI changes, validate baselines, and assess testing health dynamically.

Google ADK natively supports Applitools 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

Batch Observability — Query active test batches to view aggregated statuses (Passed, Failed, Unresolved) and completion rates
Session & Results analysis — Drill down into specific test sessions to examine failed step images, match levels, and browser differences
Baseline Management — List your "golden" graphical baselines bound to applications or specific Git branches
Actionable Maintenance — Authorize the agent to delete outdated baselines or discard legacy batches to keep your workspace clean
Key Validation — Ensure connectivity against your visual AI engine before pipeline triggers

The Applitools 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 Applitools to Google ADK via MCP

Follow these steps to integrate the Applitools 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 Applitools via MCP

Why Use Google ADK with the Applitools MCP Server

Google ADK provides unique advantages when paired with Applitools 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 Applitools

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 Applitools tools with BigQuery, Vertex AI, and Cloud Functions

Applitools + Google ADK Use Cases

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

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

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

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

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

Applitools MCP Tools for Google ADK (10)

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

delete_baseline

Use when a baseline is outdated or a page has been redesigned. Delete an Applitools test baseline

delete_batch

Does NOT affect baselines. Use with caution — this is irreversible. Delete an Applitools test batch

get_batch

Use batch ID from list_batches. Get full details of an Applitools batch

get_batch_stats

Returns passed/failed/unresolved/new counts without full test data. Get summary statistics for an Applitools batch

get_session

Provide batch ID and session ID. Get details of a test session within an Applitools batch

list_baselines

Returns baseline IDs, names, and env configs. Filter by app name. List visual baselines for an app on Applitools

list_batches

Batches group related test sessions. Returns batch IDs, names, statuses (Passed/Unresolved/Failed), and test counts. Each batch has a unique ID used to query its results. List all test batches on Applitools Eyes

list_branch_baselines

Use to inspect branch-specific visual states. List baselines for a specific branch on Applitools

list_results

List all test results in an Applitools batch

validate_key

Use to verify connectivity before running tests. Validate the Applitools API key

Example Prompts for Applitools in Google ADK

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

"List the most recent visual test batches in Applitools."

"Get me the exact session results for our unresolved batch ID b_991x."

"List the baselines assigned specifically to fixing the 'feature/dark-mode-header' branch."

Troubleshooting Applitools MCP Server with Google ADK

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

McpToolset not found

Update: pip install --upgrade google-adk

Applitools + Google ADK FAQ

Common questions about integrating Applitools 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.