How to Use the LambdaTest MCP in Google ADK

Q: How do I load the LambdaTest tools into Google ADK?

Install google-adk and configure a McpToolset using StreamableHttpServerParameters. Pass that toolset to your LlmAgent initialization. The agent will read the schema and expose the testing endpoints to Gemini.

Q: How do I stop the agent from modifying LambdaTest statuses?

Use the optional toolnames filter when setting up the MCP toolset. Exclude updatesessionstatus from the list. The agent will still read builds and logs but won't be able to change test outcomes.

Give your Gemini agents on Google ADK direct access to LambdaTest execution logs and browser matrices.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LambdaTest MCP to Google ADK

Create your Vinkius account to connect LambdaTest 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 LambdaTest with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Google ADK MCP Server Integration

The `get_test_logs` and `get_session_details` tools feed massive console outputs straight into Gemini's million-token context window. Your agent doesn't have to chunk or summarize the logs before reading them. It ingests the entire test execution history at once. This matters when you're debugging complex frontend failures. The agent pulls the full network trace from the LambdaTest session and cross-references it with your application data in BigQuery. You get root cause analysis that actually connects your cloud infrastructure to the browser rendering errors.

Test Matrix Validation

The `list_supported_platforms` tool lets your agent check which OS and browser combinations are currently available on the cloud grid. Before generating a new test script, the agent verifies the target environment exists. It stops execution if you ask for an outdated Safari version that isn't supported. Once the environment is validated, the agent monitors the execution using `list_automation_builds`. Since Google ADK handles the routing, you can deploy this agent on Vertex AI and have it continuously poll for nightly run completions without eating up local compute.

Triaging Flaky Tests

Tracking down intermittent failures requires the `list_test_sessions` and `get_build_details` tools. The agent scans a specific build, extracts every test run, and looks for patterns in the failure rates. It identifies if a test only fails on Windows 11 or if it's a global timeout issue. After analyzing the pattern, the agent uses `update_session_status` to tag false positives. You can restrict which MCP tools the agent accesses by passing a `tool_names` filter to the `McpToolset` constructor. That keeps the agent focused strictly on reading data if you don't want it modifying test outcomes.

Setup guide

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

Install `google-adk` and configure a `McpToolset` using `StreamableHttpServerParameters`. Pass that toolset to your `LlmAgent` initialization. The agent will read the schema and expose the testing endpoints to Gemini.

Yes. Because Gemini supports massive context windows, your Google ADK agent can call `get_test_logs` across dozens of sessions simultaneously. It reads the raw output without dropping crucial stack traces.

Use the optional `tool_names` filter when setting up the MCP toolset. Exclude `update_session_status` from the list. The agent will still read builds and logs but won't be able to change test outcomes.

It runs natively on Vertex AI. You deploy the agent, and it maintains the HTTP connection to the server endpoint. It polls your builds in the background and writes the analysis to your Google Cloud storage.

The tools fetch your automated test logs, session metadata, and build statuses. This data flows through the MCP protocol directly into your Google Cloud project. Gemini processes the raw test console output, so filter out PII in your test runner before execution.

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