Monitoring your AI agent can set up

Connect your agent

The server is at https://app.pingstack.io/mcp and signs you in through your browser.

claude mcp add --transport http pingstack https://app.pingstack.io/mcp

{
  "mcpServers": {
    "pingstack": {
      "url": "https://app.pingstack.io/mcp"
    }
  }
}

codex mcp add pingstack --url https://app.pingstack.io/mcp
codex mcp login pingstack

{
  "mcpServers": {
    "pingstack": {
      "serverUrl": "https://app.pingstack.io/mcp"
    }
  }
}

Steps for VS Code, Gemini CLI and API keys are in the client setup docs.

What your agent can do

• Create and update heartbeat, website, DNS, TCP and renewal checks
• Attach checks to dashboards and reorder them
• List incidents and read uptime, run history and latency percentiles for up to a year, as far back as your plan keeps, in your own time zone
• See when each check last ran and when a certificate or domain expires
• Read your plan’s limits and usage
• Read ping URLs, but only with the operational-credential permission

Guardrails

Your agent gets your role’s permissions and your plan’s limits. It can’t publish a dashboard, delete checks or buy anything. When it hits a plan limit, it hands back an upgrade link for a person to open.

Try asking

• “Add a daily heartbeat for the backup job with a 15 minute grace period and attach it to the Infrastructure dashboard.”
• “Which checks had incidents in the last 7 days, and how long were they down?”
• “Create website checks for every domain in this README.”

REST API

Everything above also works over a REST API with account-bound keys, so your scripts and CI can use it too. See the API docs.