How to Use the Healthchecks.io MCP in Pydantic AI

Q: How does Pydantic AI ensure my Healthchecks.io data is correct?

Every time your agent calls a tool like listchecks, Pydantic AI validates the JSON response against a predefined model. If the API returns anything unexpected, it raises an error instead of letting your agent proceed with bad data.

Q: What's the setup for Pydantic AI and Healthchecks.io?

It's straightforward. You create an MCPToolset instance with your Vinkius server URL and add it to your agent's toolsets list. The framework handles the rest.

Q: Is it possible to get the body of a ping request?

It is. The getpingbody tool allows your agent to fetch the content of a specific ping signal. Pydantic AI ensures the response you get is a properly-formed string.

Add type-safe Healthchecks.io monitoring to your Pydantic AI agent. Get reliable cron job data, validated on every API call.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Healthchecks.io MCP to Pydantic AI

Create your Vinkius account to connect Healthchecks.io 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 Healthchecks.io with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Reliable Check Management

Let your agent manage your Healthchecks.io setup with guaranteed correctness. Every call to `create_check` or `update_check` returns a response that Pydantic AI validates against a strict schema. No more guessing if the API returned what you expected. This means your agent can confidently `pause_check` and `resume_check` during operations. If the Healthchecks.io API ever changes or returns an error, your agent will raise a `ValidationError` immediately instead of failing silently.

Debug with Validated Data

When your agent investigates a failure, it gets clean, structured data. The output of `list_pings` and `list_flips` is parsed into Pydantic models, so you know every timestamp is a real datetime object and every status is a valid enum. This is a big deal for debugging. Your Pydantic AI agent can trust the data from `get_check` without writing defensive code. It eliminates an entire class of bugs caused by unexpected API responses.

A Type-Safe Pydantic AI Experience

Build agents that are correct by design. With `list_checks`, your agent gets a list of check objects, not just a blob of JSON. You can filter by tags and know the structure of the response is guaranteed. The same goes for `list_integrations` and `list_badges`. Pydantic AI's runtime validation means your agent operates on a foundation of trust. This MCP server gives you that trust for your entire monitoring infrastructure.

Setup guide

Set up Healthchecks.io 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": {
        "healthchecksio-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Healthchecks.io 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 Healthchecks.io. 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 Healthchecks.io 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 Healthchecks.io MCP in Pydantic AI

Every time your agent calls a tool like `list_checks`, Pydantic AI validates the JSON response against a predefined model. If the API returns anything unexpected, it raises an error instead of letting your agent proceed with bad data.

It's straightforward. You create an `MCPToolset` instance with your Vinkius server URL and add it to your agent's `toolsets` list. The framework handles the rest.

Yes. Pydantic AI is model-agnostic. You can use it with local models, OpenAI, or Anthropic to call tools like `create_check` and `get_status` for your Healthchecks.io project.

It is. The `get_ping_body` tool allows your agent to fetch the content of a specific ping signal. Pydantic AI ensures the response you get is a properly-formed string.

The server acts as a secure pass-through for Healthchecks.io metadata—things like check names, tags, and status history. Each request runs in an isolated V8 sandbox on Vinkius, authenticated with your unique token. Your information is processed in memory and never written to disk.

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