Can my AI agent stop a runaway test job automatically?

Yes. If you notice a particular build is stuck, you can tell your agent: 'Check the currently running jobs in Sauce Labs and stop any that have been running for more than 40 minutes.' The agent will use `list_jobs` and conditionally call `stop_job` on the offending ones to free up your concurrency limit.

How do I securely inspect the exact failure from an automation script?

If a CI action fails, ask the agent to 'List the latest builds.' Note the failing Build ID, request 'Get details for the failing jobs in this build'. The agent can return the exact error message, browser specs, and direct URL to the video session inside Sauce Labs.

Can the agent tell me why my cloud jobs are in a 'queued' status?

Yes. This is a common DevOps question. You can prompt: 'Check our concurrency limits and active tunnels.' The agent will use `get_concurrency` to see if your team maxed out available nodes and `list_tunnels` to ensure Sauce Connect hasn’t dropped the connection.

Sauce Labs MCP Server for Google ADK 11 tools — connect in under 2 minutes

Name: Sauce Labs
Availability: InStock
Author: Vinkius

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

Built by Vinkius GDPR 11 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Sauce Labs 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="sauce_labs_agent",
    instruction=(
        "You help users interact with Sauce Labs "
        "using 11 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 Sauce Labs MCP Server

Connect your Sauce Labs account to any AI agent to bring your entire test execution landscape directly into your chat workflow. Say goodbye to jumping between CI/CD tools and the Sauce Labs dashboard to investigate failures.

Google ADK natively supports Sauce Labs as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 11 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

Jobs & Builds — Check the status of recent test builds, drill down into specific job results, and monitor pass/fail ratios
Incident Management — Programmatically stop hung or failing jobs to free up test concurrency limits instantly
Infrastructure Metrics — Check your active Sauce Connect tunnels, current account activity, and real-time concurrency metrics
Platform Support — Browse supported OS and browser combinations (Appium, WebDriver) directly through the agent

The Sauce Labs MCP Server exposes 11 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 Sauce Labs to Google ADK via MCP

Follow these steps to integrate the Sauce Labs 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 11 tools from Sauce Labs via MCP

Why Use Google ADK with the Sauce Labs MCP Server

Google ADK provides unique advantages when paired with Sauce Labs 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 Sauce Labs

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 Sauce Labs tools with BigQuery, Vertex AI, and Cloud Functions

Sauce Labs + Google ADK Use Cases

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

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

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

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

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

Sauce Labs MCP Tools for Google ADK (11)

These 11 tools become available when you connect Sauce Labs to Google ADK via MCP:

get_activity

Retrieves current account activity levels

get_build

Retrieves details for a specific build

get_build_jobs

Lists all individual jobs within a specific build

get_concurrency

Retrieves account concurrency limits

get_job

Retrieves details for a specific test job

get_status

Checks current Sauce Labs platform availability

list_builds

Lists recent automation builds

list_jobs

). Lists recent test jobs on Sauce Labs

list_platforms

Specify all, appium, or webdriver. Lists all supported OS and browser combinations

list_tunnels

Lists active Sauce Connect tunnels

stop_job

Stops a running test job

Example Prompts for Sauce Labs in Google ADK

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

"What is our current concurrency usage vs limit in Sauce Labs?"

"Show me the jobs that failed in my last automation build."

"Stop the test job ID 4f4f391e0 because it's stuck."

Troubleshooting Sauce Labs MCP Server with Google ADK

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

McpToolset not found

Update: pip install --upgrade google-adk

Sauce Labs + Google ADK FAQ

Common questions about integrating Sauce Labs 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.