Skip to content
Crontinel Docs

MCP Integration Overview

Crontinel exposes an MCP (Model Context Protocol) server so AI coding assistants can query your monitoring data inline – without opening a browser.

Example

In Claude Code:

You: Did my send-invoices job run last night?

Claude: Checking Crontinel… The send-invoices command ran at 02:00:14 UTC, completed in 847ms, exit code 0. Last 7 runs all successful.

How it works

  1. The @crontinel/mcp-server npm package runs as a local stdio process
  2. Your AI assistant spawns it on startup
  3. It proxies tool calls to app.crontinel.com/api/mcp using your API key
  4. Results come back inline in your chat

Requirements

  • Node.js 18+
  • A Crontinel account. Prefer OAuth from the app connection screen; a scoped API key is the fallback. MCP is on every tier, including Free. Hosted AI investigation starts are a separate allowance.
  • An AI assistant that supports MCP (Cursor, Claude Code, Codex, etc.)

What you can ask

The assistant mostly reads evidence that your jobs already sent to Crontinel. Typical questions:

  • Did a named scheduled job run, and with what exit code and duration?
  • Is a queue backing up, or is Horizon paused?
  • Which alerts fired recently, and have they resolved?

The tools behind these are listed on Available Tools. Two tools change state in Crontinel (acknowledge_alert and create_alert); nothing is written to your own app or servers.

Set up your client