How to Use the Cypress Cloud MCP in Google ADK

Q: How can my Google ADK agent access Cypress Cloud test data?

You simply add the Vinkius MCP endpoint to a McpToolset in your agent's configuration. The ADK will then expose all the Cypress Cloud tools, like getruns and reportflaky, for your Gemini-powered agent to use.

Q: What's the best way to get started with Cypress Cloud and Google ADK?

Start simple. Build an agent that uses listprojects to find your project ID, then calls getruns to list the last few test runs. From there, you can add more complex logic, like drilling down into failed runs or generating reports.

Connect Google ADK agents to Cypress Cloud. Feed test data into BigQuery and analyze long-term trends with Gemini's long-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 Cypress Cloud MCP to Google ADK

Create your Vinkius account to connect Cypress Cloud 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 Cypress Cloud with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Cypress Data into BigQuery

Turn your Cypress Cloud test results into structured data for analysis. An agent built with Google ADK can use `get_runs` and `get_tests` to fetch test data, then pipe it directly into BigQuery tables. This gives you a historical record of every test run, ready for complex querying. Go beyond simple pass/fail. Your agent can periodically run `report_slow` and `report_flaky`, storing the results in BigQuery. Now you can track test performance and stability trends over months, correlating them with code changes or infrastructure updates, all within the Google Cloud ecosystem.

Analyze Test Failures with Gemini

A failed run generates a lot of data. Your Gemini agent can handle it. Use `get_run`, `get_instances`, and `get_tests` to pull all the details of a failure—error messages, test titles, browser info—into its massive context window. With all the data in context, the agent can reason about the root cause. It can compare a failed run to a previous successful one, spot patterns in the errors, and suggest a likely cause. This MCP Server provides the raw material for Gemini's analytical power.

Automate Reporting on Google Cloud

Automate your engineering health metrics. Set up a scheduled agent to call `report_runs` and `report_tests` for enterprise-level summaries. The agent can format this data and push it to Google Sheets or a BI tool connected to Vertex AI. The `list_projects` tool is your starting point. An agent can use it to discover all available Cypress projects, then systematically gather data from each one. This is perfect for platform teams managing testing across an entire organization on Google Cloud.

Setup guide

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

You simply add the Vinkius MCP endpoint to a `McpToolset` in your agent's configuration. The ADK will then expose all the Cypress Cloud tools, like `get_runs` and `report_flaky`, for your Gemini-powered agent to use.

Absolutely. That's a core strength. Your agent can use this MCP server to get the timestamp and `ci_build_id` from a failed run with `get_run`, then use other tools to query Google Cloud Logging for relevant logs from that exact timeframe.

Start simple. Build an agent that uses `list_projects` to find your project ID, then calls `get_runs` to list the last few test runs. From there, you can add more complex logic, like drilling down into failed runs or generating reports.

This specific MCP server is built only for Cypress Cloud. It uses the Cypress Cloud API to provide tools for accessing your E2E test data.

The server only reads test metadata from Cypress Cloud—run status, test names, error messages, and durations. It never touches your source code. Each request is processed in an isolated, ephemeral Vinkius sandbox, and the server's permissions are strictly read-only.

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