How to Use the Gatus (Health Dashboard) MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK use getendpointhealth with Gatus (Health Dashboard)?

Your agent calls getendpointhealth to get a structured JSON response about a service's status. The SDK's guardrails then let you review the agent's proposed next step, like escalating a ticket, before it executes.

Build production-ready monitoring agents with the OpenAI Agents SDK that react to real-time health data from your Gatus dashboard.

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 OpenAI Agents SDK

Create your Vinkius account to connect Gatus (Health Dashboard) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Check Service Health, Safely

The `get_endpoint_health` tool lets your agent check if a service is up. Is the API responding? Is the database connection alive? Your agent gets a clear yes or no. Because you're using the OpenAI Agents SDK, the agent can't just act on this data without your approval. It proposes an action—like paging an on-call engineer—and the SDK's guardrails let you confirm it first. It's a safer way to automate responses to downtime.

Trace Outages with OpenAI

Use `list_endpoints` to give your agent a full map of your monitored infrastructure. When an alert fires, the agent can then use `get_endpoint_stats` to pull latency and uptime figures for related services, looking for the source of the problem. Every one of these calls is logged and traceable in your OpenAI dashboard. You get a full audit trail of how the agent diagnosed the problem, step-by-step. No more guessing what your automation did.

Analyze Metrics with your MCP Server

The `get_metrics` tool pulls raw Prometheus-formatted metrics from Gatus. Your agent can parse this data to spot trends that a simple up/down check would miss, like slowly degrading response times. This is where the OpenAI ecosystem helps. You can have one agent fetch the data with this MCP Server, then hand it off to a specialized data analysis agent to look for anomalies. The final result gets passed back to your main operations agent for action.

Setup guide

Set up Gatus (Health Dashboard) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Gatus (Health Dashboard) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Gatus (Health Dashboard) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Gatus (Health Dashboard) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Gatus (Health Dashboard) Agent",
            instructions="You have access to Gatus (Health Dashboard) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Your agent calls `get_endpoint_health` to get a structured JSON response about a service's status. The SDK's guardrails then let you review the agent's proposed next step, like escalating a ticket, before it executes.

Yes. While the SDK auto-discovers all tools by default, you can configure your agent to only use a specific subset. This lets you restrict it to read-only tools like `list_endpoints` and `get_metrics` for safety.

This server integrates Gatus data directly into the SDK's safety features. You get traceable, reviewable actions that you don't get from a simple script. Vinkius also handles the connection and auth, so you don't have to.

Yes, the server is a thin layer over the Gatus API. For the best performance with the OpenAI Agents SDK, set `cacheToolsList=True` in your agent's configuration so it doesn't have to fetch the tool list on every run.

The server only reads your Gatus instance's health status, endpoint configuration, and performance metrics. Vinkius isolates each server request in an ephemeral sandbox, and your agent's actions are secured by the SDK's built-in guardrails. No data is stored.

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