Can I trigger an API check manually through the agent?

Yes! Use the `trigger_check_run` tool with the unique check ID. The agent will instruct Checkly to run the test immediately from its global network.

How do I see the performance metrics for my homepage check?

Use the `get_check_performance_metrics` tool with the check ID. Your agent will fetch detailed analytics including success rates and response time percentiles.

Where do I find my Checkly API Key and Account ID?

Log in to your Checkly account and navigate to **User Settings -> API Keys** for the key. The **Account ID** can be found in the **Account Settings** section.

Checkly MCP Server for OpenAI Agents SDK 8 tools — connect in under 2 minutes

Name: Checkly
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 8 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Checkly through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Checkly Assistant",
            instructions=(
                "You help users interact with Checkly. "
                "You have access to 8 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Checkly"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Checkly MCP Server

Connect your Checkly account to any AI agent and take full control of your application monitoring and synthetic testing through natural conversation. Streamline how you ensure the uptime and performance of your APIs and web apps.

The OpenAI Agents SDK auto-discovers all 8 tools from Checkly through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Checkly, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Check Oversight — List and retrieve details for all API and Browser monitors natively
Live Execution — Manually trigger check runs to verify system health on-demand flawlessly
Performance Intelligence — Access detailed performance metrics and response times for any monitor securely
Alert Management — List and audit all configured alert channels (Slack, Email, PagerDuty) flawlessly
Reliability Tracking — Monitor heartbeat and cron jobs to ensure your background tasks are running flawlessly
System Metadata — Retrieve core account information and organizational structures directly within your workspace

The Checkly MCP Server exposes 8 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Checkly to OpenAI Agents SDK via MCP

Follow these steps to integrate the Checkly MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 8 tools from Checkly

Why Use OpenAI Agents SDK with the Checkly MCP Server

OpenAI Agents SDK provides unique advantages when paired with Checkly through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Checkly + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Checkly MCP Server delivers measurable value.

Automated workflows: build agents that query Checkly, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Checkly, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Checkly tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Checkly to resolve tickets, look up records, and update statuses without human intervention

Checkly MCP Tools for OpenAI Agents SDK (8)

These 8 tools become available when you connect Checkly to OpenAI Agents SDK via MCP:

get_check_details

Get detailed information for a specific check

get_check_performance_metrics

Retrieve performance metrics for a specific check

get_checkly_account_info

Retrieve core account and organization metadata

list_check_groups

List groups of checks

list_checkly_alert_channels

List all configured alert channels (Slack, Email, PagerDuty, etc)

list_checkly_checks

List all API and Browser checks

list_checkly_heartbeats

List all heartbeat (cron) monitors

trigger_check_run

Manually trigger a check to run immediately

Example Prompts for Checkly in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Checkly immediately.

"List all my monitors in Checkly and their last status."

"Show me the response time graph for the 'Checkout Flow' check."

"Check the status of my heartbeat monitors."

Troubleshooting Checkly MCP Server with OpenAI Agents SDK

Common issues when connecting Checkly to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Checkly + OpenAI Agents SDK FAQ

Common questions about integrating Checkly MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.