How to Use the Checkly MCP in Windsurf

Q: How does Windsurf use Checkly to debug failing tests?

Cascade calls getcheckdetails to pull the exact failure logs from your dashboard. It then searches your local codebase, writes a fix, and runs triggercheckrun to verify the error is gone.

Q: Can I trigger a Checkly run from Windsurf Cascade?

Yes. Cascade uses the triggercheckrun tool to execute live checks instantly. You get the execution results back in your chat window within seconds.

Q: How do I monitor cron jobs using this setup?

The server exposes listchecklyheartbeats to let your agent inspect your active cron monitors. You can ask Cascade to list failing heartbeats and correlate them with recent git commits.

Let Windsurf autonomously run Checkly API checks, pull performance metrics, and fix broken endpoints without leaving your editor.

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 Windsurf

Create your Vinkius account to connect Checkly to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debug failing endpoints directly in Windsurf Cascade

The `get_check_details` tool fetches the exact status and failure reasons for your monitored APIs. Cascade reads this payload, spots the failing assertion, and immediately hunts down the broken code in your local workspace to fix it. You do not have to copy-paste error logs from a browser tab anymore. Cascade runs `list_checkly_checks` to map your remote monitors to local files, making debugging a single-prompt job.

Run Checkly MCP Server tests on demand

The `trigger_check_run` tool lets Cascade start any API or browser check instantly to verify your latest local changes. Instead of waiting for a scheduled run, your AI client fires the check, polls the status, and confirms the fix works. This tight feedback loop keeps your deployment pipeline clean. Cascade coordinates the run, checks the performance with `get_check_performance_metrics`, and tells you if your code slowed down the endpoint.

Map your entire monitoring architecture with MCP

The `list_check_groups` tool pulls your organized monitors so Cascade can map out your application's dependency graph. This gives your agent the context it needs to understand which microservices affect which user journeys. Cascade also queries `list_checkly_alert_channels` and `list_checkly_heartbeats` to verify your cron monitors and notification paths are active. You get a complete picture of your production health without opening the Checkly dashboard.

Setup guide

Set up Checkly MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Checkly MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Checkly payment history." If connected, Cascade will call the Checkly tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "checkly-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Windsurf

Cascade calls `get_check_details` to pull the exact failure logs from your dashboard. It then searches your local codebase, writes a fix, and runs `trigger_check_run` to verify the error is gone.

Yes. Cascade uses the `trigger_check_run` tool to execute live checks instantly. You get the execution results back in your chat window within seconds.

No. Once you add the server to your configuration, Cascade auto-discovers all eight tools. You can start asking it to inspect your monitors right away.

The server exposes `list_checkly_heartbeats` to let your agent inspect your active cron monitors. You can ask Cascade to list failing heartbeats and correlate them with recent git commits.

Your API keys and monitoring configurations are processed within an isolated V8 sandbox using our secure MCP transport. The server only accesses your check configurations and alert channels to run tests, and your credentials never leak to the LLM provider.

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