How to Use the Checkly MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK trigger Checkly runs automatically?

Yes, your agent can call the triggercheckrun tool based on specific conditions. You define the guardrails to ensure it only happens when safe. The execution trace will show up in your OpenAI dashboard.

Monitor API uptime and trigger test runs directly from your production OpenAI Agents SDK deployments using this MCP server.

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 OpenAI Agents SDK

Create your Vinkius account to connect Checkly 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 Checkly with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Checkly MCP Server incident response

Your agent needs to know when endpoints fail. Calling `list_checkly_checks` pulls the current status of every API and browser monitor in your account. You get immediate visibility into failing tests without leaving your Python execution environment. Handoffs between specialized agents become much safer here. One agent spots a failure and uses `get_check_details` to grab the exact error context. It then passes that payload to a separate remediation agent, fully tracked in your OpenAI dashboard.

Trigger immediate test runs

Waiting for cron schedules delays deployments. Your pipeline agent can fire off a `trigger_check_run` command the second a staging build finishes. This forces Checkly to evaluate the new code right now. Built-in guardrails validate the action before execution. If the agent tries to run a destructive test against production, your safety constraints block the request. You keep full control over when and how monitors execute.

Analyze performance metrics

Latency spikes degrade user experience fast. Fetching `get_check_performance_metrics` gives your agent the historical response times for any specific monitor. The model can then compare current degradation against baseline averages. Grouping data helps isolate regional issues. The agent runs `list_check_groups` to see if a slowdown affects an entire cluster or just one isolated endpoint. All tool calls auto-discover via the MCP protocol, requiring zero manual schema mapping.

Setup guide

Set up Checkly 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 Checkly tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Checkly 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="Checkly Agent",
            instructions="You have access to Checkly 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 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 OpenAI Agents SDK

Use MCPServerStreamableHttp with your Vinkius endpoint URL. Pass it in the mcp_servers array to your Agent constructor. Setting cacheToolsList=True speeds up the initial connection.

Yes, your agent can call the trigger_check_run tool based on specific conditions. You define the guardrails to ensure it only happens when safe. The execution trace will show up in your OpenAI dashboard.

It pulls monitor status, heartbeat logs, and alert configurations. Tools like list_checkly_heartbeats and list_checkly_alert_channels expose your exact monitoring setup. The agent uses this to map out your alerting topology.

The integration handles both API and browser monitors. Calling list_checkly_checks returns the full inventory. You get the same detail level regardless of the test type.

Vinkius runs the server in an ephemeral V8 Isolate Sandbox. Your API response times, endpoint URLs, and alert channel webhooks never touch disk. The connection terminates immediately after the tool call finishes.

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