How to Use the Gatus (Health Dashboard) MCP in Google ADK

Q: How can I use Google ADK to analyze data from the Gatus (Health Dashboard)?

Your agent can call getmetrics to get raw data, then use other Google Cloud tools to push it to BigQuery. From there, you can analyze historical uptime and performance trends across all your monitored services.

Q: How do I set up the Gatus (Health Dashboard) MCP Server with Google ADK?

You instantiate an McpToolset with the server URL and pass it to your LlmAgent. Google ADK handles the tool discovery, letting your Gemini agent call Gatus functions like getendpointhealth as if they were native Python methods.

Connect your Gatus dashboard to Gemini agents on Google Cloud. Analyze health metrics at scale with Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gatus (Health Dashboard) MCP to Google ADK

Create your Vinkius account to connect Gatus (Health Dashboard) 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 Gatus (Health Dashboard) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Gatus Metrics into BigQuery

Use `get_metrics` to pull all Prometheus-compatible metrics from your Gatus instance. Your Gemini agent can take this raw text data and feed it directly into a BigQuery table for long-term analysis. Now you can run complex SQL queries over months of uptime data. You can correlate Gatus metrics with other business data in your data warehouse and build Looker dashboards to visualize long-term service health.

Long-Context Incident Diagnosis

The `list_endpoints` and `get_endpoint_health` tools give your agent the lay of the land. It can check the status of dozens of services in a single, fluid conversation. With Gemini's long-context window, your agent can hold the status of your entire infrastructure in memory. It can reason about cascading failures by comparing the output of `get_endpoint_stats` across multiple failing services, spotting connections a human might miss during a chaotic incident.

Automate with your Google ADK MCP Server

This MCP server is the bridge between your Gatus monitoring and the rest of your Google Cloud setup. Your agent can use `get_endpoint_health` to detect a failure and then trigger a Cloud Function or a Vertex AI pipeline. You can filter the tools exposed to the agent using the `tool_names` parameter in the `McpToolset`. This lets you create specialized agents—one that only reads metrics, another that can only list endpoints—for better security within your GCP projects.

Setup guide

Set up Gatus (Health Dashboard) 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 Gatus (Health Dashboard) 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="Gatus (Health Dashboard)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Gatus (Health Dashboard) 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 Gatus. 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 Gatus (Health Dashboard) 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 Gatus (Health Dashboard) MCP in Google ADK

Your agent can call `get_metrics` to get raw data, then use other Google Cloud tools to push it to BigQuery. From there, you can analyze historical uptime and performance trends across all your monitored services.

Yes. An agent powered by a model like Gemini can use tools like `list_endpoints` and `get_endpoint_stats` to gather data on all your services. It can hold it all in context to perform a more complex root cause analysis.

You instantiate an `McpToolset` with the server URL and pass it to your `LlmAgent`. Google ADK handles the tool discovery, letting your Gemini agent call Gatus functions like `get_endpoint_health` as if they were native Python methods.

This is a managed MCP server hosted by Vinkius. You just give your agent the Vinkius endpoint URL. It connects securely to your Gatus dashboard without you needing to manage another piece of infrastructure.

The server only accesses Gatus endpoint health statuses and performance metrics on your behalf. Each request is handled in a zero-trust, ephemeral environment on Vinkius. The connection is stateless and no Gatus data is ever persisted by the server.

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