How to Use the Gatus (Health Dashboard) MCP in Pydantic AI

Q: Why use the Gatus (Health Dashboard) MCP Server with Pydantic AI?

It guarantees that the data from Gatus tools like getendpointhealth is type-safe. If the API returns something unexpected, Pydantic AI will raise an error instead of letting your agent proceed with bad data.

Q: How do I connect Pydantic AI to this MCP Server?

Just create an MCPToolset with the server URL provided by Vinkius. Pass that toolset to your Pydantic AI Agent, and it will automatically discover and set up validation for the Gatus tools.

Get type-safe, validated Gatus health data in your Python agents with Pydantic AI. No more guessing API schemas.

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 Pydantic AI

Create your Vinkius account to connect Gatus (Health Dashboard) to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Runtime Data Validation

The `get_endpoint_health` tool returns a JSON object with the status of a service. With Pydantic AI, that JSON is automatically parsed and validated against a Pydantic model before your agent's code ever sees it. If Gatus ever changes its API response or returns an unexpected error, your agent raises a `ValidationError` immediately. This stops your agent from acting on corrupted or misunderstood data, which is critical for automated monitoring.

Model-Agnostic Monitoring

This MCP server provides the Gatus tools—`list_endpoints`, `get_endpoint_stats`, etc.—in a standard format. Pydantic AI lets you plug them into any LLM you want, whether it's from OpenAI, Google, Anthropic, or a local model running on your own hardware. You aren't locked into one provider's ecosystem. You can build your monitoring agent with the LLM that works best for your needs and budget. If you want to swap it out later, you don't have to rewrite all your tool-calling logic.

Build Correct-by-Construction Agents

The `get_metrics` tool exposes raw Prometheus metrics. By defining a Pydantic model for the expected metric format, you force your agent to only process data that conforms to your exact schema. This approach turns runtime surprises into predictable validation errors during development. It helps you build a more robust and reliable monitoring agent from the start. That's the core benefit of using this MCP server with Pydantic AI.

Setup guide

Set up Gatus (Health Dashboard) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "gatus-health-dashboard-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Gatus (Health Dashboard) tools.",
)

result = await agent.run("List recent Gatus (Health Dashboard) transactions")
print(result.output)

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 Pydantic AI

It guarantees that the data from Gatus tools like `get_endpoint_health` is type-safe. If the API returns something unexpected, Pydantic AI will raise an error instead of letting your agent proceed with bad data.

If the Gatus server returns data that doesn't match the expected Pydantic model for a tool like `get_endpoint_stats`, Pydantic AI raises a `ValidationError`. This gives you an immediate, loud failure instead of silent data corruption downstream.

Yes, Pydantic AI is model-agnostic. You can use this MCP server to feed validated Gatus health data to an agent running on a local model just as easily as one using a commercial API.

Just create an `MCPToolset` with the server URL provided by Vinkius. Pass that toolset to your Pydantic AI `Agent`, and it will automatically discover and set up validation for the Gatus tools.

The server only requests your Gatus dashboard's endpoint health and metric data when your agent calls a tool. Your Vinkius auth token secures the connection, and every request is processed in a dedicated sandbox that is destroyed after the call completes. Your Gatus data is never stored or logged.

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