How to Use the Checkly MCP in Pydantic AI

Q: Can Pydantic AI read Checkly account info?

The getchecklyaccountinfo tool fetches your organization metadata directly. Your agent uses this to tag reports with the correct account details. Strict typing ensures the account ID format is always correct.

Build type-safe Checkly MCP monitoring agents with Pydantic AI that validate every API response at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Checkly MCP to Pydantic AI

Create your Vinkius account to connect Checkly 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 Checkly with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe MCP test execution

Silent failures ruin automated testing pipelines. Firing `trigger_check_run` through this integration guarantees that the response matches your exact schema expectations. If the Checkly API returns an unexpected payload structure, the framework throws a loud validation error immediately. Hallucinated fields simply cannot exist here. The agent processes the execution results knowing the data type is strictly enforced. You get absolute confidence that your deployment decisions rely on real monitor outputs.

Extract deep check details

Debugging broken endpoints requires context. Requesting `get_check_details` pulls the complete configuration and recent history for a specific monitor. The agent parses this data to figure out exactly why an API route started failing. Switching between LLM providers changes nothing about this workflow. Because the framework is model-agnostic, you can use Anthropic for complex debugging and a local model for basic status checks. The Pydantic models validate the server output exactly the same way.

Map monitoring infrastructure

Auditing your coverage manually takes too much time. Using `list_checkly_checks` alongside `list_check_groups` allows your agent to build a complete inventory of your monitoring setup. It identifies which critical services lack active browser tests. Correctness matters more than speed during an infrastructure audit. Every group ID and check name gets verified against your predefined models. The agent builds a reliable report that you can confidently present to your engineering team.

Setup guide

Set up Checkly 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": {
        "checkly-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Initialize an MCPToolset with your Vinkius HTTP endpoint URL. Pass it via the toolsets argument when creating your Agent. Make sure you install the pydantic-ai-slim[mcp] package first.

Runtime validation prevents the agent from acting on malformed data. If a Checkly tool returns an unexpected string instead of a list, the system fails loudly. You avoid silent corruption in your automated workflows.

The get_checkly_account_info tool fetches your organization metadata directly. Your agent uses this to tag reports with the correct account details. Strict typing ensures the account ID format is always correct.

The unified toolset approach supports both Streamable HTTP and SSE transports. You just provide the external URL provided by Vinkius. The deprecated MCPServerHTTP class is no longer required.

Vinkius hosts this integration in an ephemeral, zero-trust environment. Your custom browser check scripts, API headers, and assertion logic are processed entirely in memory. The container vanishes completely once the Pydantic model receives the validated response.

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