How to Use the Checkly MCP in Claude Code

Q: How do I add the Checkly MCP Server to Claude Code?

Run the claude mcp add command in your terminal, specifying the transport and the server URL. Claude Code will automatically load all eight monitoring tools.

Q: Can I use Claude Code to run a Checkly check manually?

Yes. Claude Code uses triggercheckrun to execute any API or browser check instantly from your terminal, returning the results directly to your shell.

Q: Can Claude Code help me audit my Checkly alert configurations?

Yes. Claude Code queries listchecklyalertchannels to list your active alert channels, letting you verify that your paging systems are set up correctly.

Q: How is my Checkly account info protected?

Your account metadata, pulled via getchecklyaccountinfo, is encrypted in transit and processed within a secure V8 isolate using our secure MCP gateway. We do not store your API tokens, and your monitoring data is never cached on our servers.

Run Checkly API monitoring tasks, trigger instant checks, and inspect performance directly from Claude Code in your terminal.

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 Claude Code

Create your Vinkius account to connect Checkly to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger terminal-driven Checkly MCP Server tests

The `trigger_check_run` tool executes any API or browser check immediately from your shell environment. Claude Code runs the check, streams the progress, and reports the pass/fail status directly to your terminal. You do not need to open a web browser to verify a deployment. The agent handles the execution and uses `get_check_details` to show you exactly why a check failed if things go south.

Inspect production performance metrics

The `get_check_performance_metrics` tool retrieves latency percentiles and uptime stats for any monitored endpoint. Claude Code pipes this data into your terminal, letting you analyze speed regressions during a deployment. This terminal-first approach lets you script performance checks. The agent runs `list_checkly_checks` to find your target endpoint, pulls the metrics, and alerts you if latency exceeds your thresholds.

Audit alerts and cron monitors from the shell

The `list_checkly_heartbeats` tool fetches all active cron monitors to let you check background job health from the command line. Claude Code displays silent failures and missing check-ins instantly. The agent also runs `list_checkly_alert_channels` and `list_check_groups` to verify your alerting setup. You can quickly audit which channels receive alerts for each service group without leaving your SSH session.

Setup guide

Set up Checkly MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see checkly-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Checkly transactions." It will automatically discover and invoke the available Checkly tools.

Terminal

claude mcp add --transport http checkly-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "checkly-mcp": {
      "type": "url",
      "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 Claude Code

Run the `claude mcp add` command in your terminal, specifying the transport and the server URL. Claude Code will automatically load all eight monitoring tools.

Yes. Claude Code uses `trigger_check_run` to execute any API or browser check instantly from your terminal, returning the results directly to your shell.

Yes. Claude Code queries `list_checkly_alert_channels` to list your active alert channels, letting you verify that your paging systems are set up correctly.

Yes. Because this client is headless, you can run it inside GitHub Actions or Docker containers to query check statuses and performance metrics programmatically.

Your account metadata, pulled via `get_checkly_account_info`, is encrypted in transit and processed within a secure V8 isolate using our secure MCP gateway. We do not store your API tokens, and your monitoring data is never cached on our servers.

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