How to Use the BugBug MCP in Google ADK

Q: Can Google ADK filter which BugBug tools are available?

Yes, use the toolnames filter when initializing the McpToolset. This restricts the agent to only the specific BugBug functions you want it to use.

Q: Is BugBug compatible with Google ADK long-context models?

It is. You can feed the results of listsuites into your Gemini models to analyze test coverage across massive web applications.

Q: Does BugBug expose its IP addresses to Google ADK?

Yes, the getips tool is available. You can use it to verify that your cloud environment is correctly configured to reach the test runner.

Deploy BugBug tests within your Google ADK agent framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BugBug MCP to Google ADK

Create your Vinkius account to connect BugBug 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 BugBug with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run BugBug tests from Google ADK

Execute specific test suites using `run_suite` or verify single test cases with `run_test` inside your Gemini-powered agent. This allows your agent to react to code changes automatically. Your agent pulls live feedback on these actions using `get_test_run`. It makes decisions based on the actual status of your browser tests.

Query BugBug project data in Google ADK

Fetch your full test catalog using `list_tests` and `list_suites` so your agent understands the scope of your current web application coverage. List your available projects with `list_projects` to switch contexts between different web properties. This provides the agent with the necessary metadata to manage multiple testing environments.

Monitor testing activity through Google ADK

Review recent activity with `list_test_runs` and `list_suite_runs` to identify patterns in your test failures. You get a clear picture of how often your web app regressions occur. Retrieve status details for ongoing runs using `get_suite_run` to ensure your agent stays informed. This keeps your Google Cloud-based workflows synchronized with your browser testing results.

Setup guide

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

Pass the server parameters to the McpToolset object. Your Google ADK agent will then have access to the full suite of browser testing tools.

Yes, use the tool_names filter when initializing the McpToolset. This restricts the agent to only the specific BugBug functions you want it to use.

It is. You can feed the results of `list_suites` into your Gemini models to analyze test coverage across massive web applications.

Yes, the `get_ips` tool is available. You can use it to verify that your cloud environment is correctly configured to reach the test runner.

Your test run status and project IDs are encrypted in transit. We never log or retain the underlying web application data your tests interact with.

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

Mastra AI sdk-typescript

Start using the BugBug MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started