Drumbeats MCP

Run your monitoring from your AI client.

The official Drumbeats MCP server. Let Claude, Cursor, VS Code, or any MCP client create monitors, triage incidents, and run HTTP, SSL, and DNS checks in plain language. Install in one command.

Create a free account, then mint your key.

Coming soon

From zero to first answer in three steps

Mint a key, install the server, then just ask.

1

Mint a key

An account-scoped key (dk_…) that works across every project you own. Mint your key →
2

Install

One command — npx -y @drumbeats/mcp. Pick your client →
3

Ask

Talk to your monitoring in plain language: "List my monitors" or "Is example.com up?"

Connect your client

Get a key at Account → API keys, then add the server. Requires Node.js 22 when running via npx.

Fastest: install the bundle

Download the latest .mcpb bundle, double-click it, and paste your key when prompted.

Download the bundle

Or add it manually to claude_desktop_config.json:

json
{
  "mcpServers": {
    "drumbeats": {
      "command": "npx",
      "args": ["-y", "@drumbeats/mcp"],
      "env": { "DRUMBEATS_API_KEY": "dk_your_key" }
    }
  }
}

Restart your client, then ask it to list your monitors.

14 tools, one shared layer

Everything your AI client needs to run and watch your monitoring.

Monitors & projects

  • list_projects

    List the projects your key can access, with channels and groups.

  • create_monitor

    Create a monitor — cron, heartbeat, or HTTP uptime.

  • list_monitors

    List a project's monitors with type, status, and schedule.

  • get_monitor

    Fetch one monitor by id, with its full configuration.

  • update_monitor

    Update an existing monitor with a partial patch.

  • pause_monitor

    Pause a monitor — stops checks and alerts.

  • resume_monitor

    Resume a paused monitor.

Observe & triage

  • get_monitor_history

    Recent pings, checks, and response times for a monitor.

  • get_uptime_summary

    Project-wide uptime / SLA rollup across monitors.

  • list_incidents

    List incidents — downtime and missed runs — by status or monitor.

  • manage_incident

    Get, acknowledge, or resolve an incident.

Diagnostics

No API key
  • check_http

    Check a URL's reachability, status code, and response time.

  • check_ssl

    Inspect a TLS certificate — validity, expiry, and issuer.

  • check_dns

    Resolve a hostname and report its DNS records.

Things to ask it

Copy a prompt and paste it into your client.

List all my monitors and their current status.

Create a cron monitor for my nightly backup that runs every day at 02:00 UTC.

What's my uptime this month?

Show me open incidents and acknowledge the most recent one.

Is https://example.com up right now?

Is the SSL certificate for example.com about to expire?

Works with no account

The check_http, check_ssl, and check_dns tools need no Drumbeats account and no API key. Point any client at the server and start checking before you sign up — just omit the env entirely:

json
{
  "mcpServers": {
    "drumbeats": {
      "command": "npx",
      "args": ["-y", "@drumbeats/mcp"]
    }
  }
}

Is https://example.com up right now?

Is the SSL certificate for example.com about to expire?

Then create a free account →

Tell your coding agent

Paste this into your AGENTS.md (or CLAUDE.md) so your coding agent knows the Drumbeats MCP is available.

markdown
## Monitoring (Drumbeats MCP)

The Drumbeats MCP server is available. Use it for uptime, cron, and
heartbeat monitoring of this project.

- Find the project with `list_projects`, then `create_monitor` /
  `list_monitors` to set up and review monitors.
- Triage failures with `list_incidents` and `manage_incident`.
- Ad-hoc `check_http` / `check_ssl` / `check_dns` need no API key.

The full source is on GitHub.