- EXECUTION
- VERIFICATION
- AUDIT
- HUMAN
Short answer
How can I trigger and verify Checkly checks with my AI?
Your agent uses Checkly tools to kick off specific check runs and then pulls the detailed results for you to review. You'll get instant confirmation that your fixes or deployments actually work without leaving your chat interface.
The outcomes.
What you get from your agent.
The AI handles the execution and data retrieval so you can focus on the code.
EXECUTION
Immediate test runs
The AI triggers specific checks on demand. You get the results of the run without manual clicking.
VERIFICATION
Detailed result inspection
Your agent pulls the specific details of a check run. You'll see exactly what passed or failed.
AUDIT
Check history review
The AI lists previous checks to help you track stability over time. You can compare current results against older runs.
HUMAN
Manual intervention
The AI identifies failures but you decide how to fix the underlying code. You remain in control of the deployment logic.
The workflow
What your AI does when you request a check.
The agent moves from triggering the test to analyzing the output.
Start the test
The agent tells Checkly to run a specific check immediately.
trigger_check_runFind the run
The agent looks through your recent activity to locate the specific check you just started.
list_checkly_checksGet the data
The agent pulls the full technical breakdown of the check results.
get_check_detailsReport findings
The agent summarizes whether the check passed or failed based on the retrieved data.
get_check_details
Try it
Copy these to start.
Use these prompts to get moving.
Starting points
Replace the bracketed text with your actual Checkly check names or IDs.
Checkly Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_ZKVvNJK1bEgGdJP2vFYcWaZwHDzM0XtD3oz2UTx3/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Checkly capabilities are ready to use.
{
"mcpServers": {
"checkly-mcp": {
"url": "https://edge.vinkius.com/vk_preview_ZKVvNJK1bEgGdJP2vFYcWaZwHDzM0XtD3oz2UTx3/mcp"
}
}
}Trigger a new check run for the 'Homepage Load' check in Checkly.
List my recent Checkly checks to see if the last deployment passed.
Get the details for the last check run to see why it failed.
Run the 'API Endpoint' check and tell me if the status code is 200.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Checkly once, then ask.
Just link your account once. Your credentials stay encrypted and you can start running checks through any compatible client immediately.
Connect Checkly to your AIFAQ
How this task behaves
- 01
Can my AI create new Checkly checks?
No. The AI can only trigger existing checks, list them, or get details on them.
- 02
Does the AI change my Checkly configuration?
No. The AI only interacts with the execution and reporting of checks. It cannot modify your test scripts or settings.
- 03
How does the AI know which check to run?
You tell the AI the name or ID of the check you want to trigger in your prompt.
- 04
Can the AI fix the code if a check fails?
No. The AI reports the failure and the details, but you must perform the actual code fix yourself.
- 05
Can I see a list of all my checks?
Yes, the AI can list your available checks so you can pick the right one to run.
More questions about Checkly? The Connector page answers them. See everything the Checkly Connector can do
Connect Checkly to Claude, Cursor, ChatGPT & more
