Tools

MCP Server

Connect Claude, ChatGPT, Cursor or any MCP client to Uptimy, and ask your assistant about your monitoring.

Overview

Uptimy runs a remote Model Context Protocol server. Add it to an AI assistant and you can ask what's down, how a service has performed this week, or why last night's incident opened, and have the assistant post the status page update or schedule the maintenance window for you.

Server URL
https://mcp.upti.my/mcp

It works with any client that supports remote MCP servers over Streamable HTTP. You sign in with your Uptimy account, so there's no key to copy.

MCP or uptimyctl?

Use the MCP server in chat assistants like Claude and ChatGPT, which can't run commands. If your agent has a terminal, like Claude Code or Cursor, uptimyctl works too and covers more: it keeps the whole workspace in a file your agent edits (uptimyctl plan, then uptimyctl apply). The MCP server adds things and changes some, but deletes nothing: deleting stays in the app and the CLI.

Connect your assistant

Claude

In Claude, open Customize → Connectors, choose + Add → Add custom connector and enter https://mcp.upti.my/mcp. Claude opens Uptimy to sign in.

ChatGPT

Add a custom connector in ChatGPT's connector settings with the same URL. ChatGPT sends you to Uptimy to sign in.

Claude Code

terminal
claude mcp add --transport http uptimy https://mcp.upti.my/mcp

Then run /mcp in Claude Code, pick uptimy and choose Authenticate.

Cursor and other clients

In Cursor, use Add to Cursor, or add the server to mcp.json yourself. Other clients take the same URL and sign in the same way.

~/.cursor/mcp.json
{
  "mcpServers": {
    "uptimy": {
      "url": "https://mcp.upti.my/mcp"
    }
  }
}

For clients without sign-in support, create an API key under Settings → API Keys and send it as a header instead:

mcp.json
{
  "mcpServers": {
    "uptimy": {
      "url": "https://mcp.upti.my/mcp",
      "headers": { "Authorization": "Bearer upt_..." }
    }
  }
}

Signing in and access

When you connect, your assistant opens an Uptimy page that names the app asking for access and the address it will send you back to. Sign in (or create an account), choose the workspace the assistant may see, and approve. You're sent back to the assistant and it's ready.

  • Each connection is to one workspace. To use another, connect again and pick it.
  • Approving creates an API key named after the app, like Claude (MCP), with full access to that workspace for 90 days. After that, the assistant asks you to sign in again.
  • You can see these keys, marked AI assistant, under Settings → API Keys, with when each was last used. Revoking one disconnects the assistant within a few minutes.
  • Approving needs permission to create API keys in the workspace.

Tools

The server offers twenty-four tools: ten that read and fourteen that change things in your workspace.

ToolKindWhat it does
get_status_overviewReadEvery monitor and heartbeat with its current status, open incidents, status pages, and the third-party services you follow, problems first. The assistant starts here.
get_monitorReadOne monitor or heartbeat: target, schedule, regions, status, and for heartbeats the last check-in and ping URL.
get_monitor_metricsReadUptime and latency over a time range (24 hours by default): totals, each region, a time series, and the most recent failed checks with their errors.
list_incidentsReadRecent incidents, newest first, filtered by open or resolved and by severity.
get_incidentReadOne incident with its timeline of updates and status changes, and the status pages it's shown on.
get_dependenciesReadThe third-party services Uptimy measures (GitHub, Cloudflare, Stripe, ...), which ones you follow, and for one service its probes, status and uptime. Tells your problem apart from a provider's.
list_reportsReadThe workspace's uptime reports: what each covers (every monitor, or one client's), its SLA target and its email schedule.
get_uptime_reportReadAvailability against the SLA target for the last 7, 30 or 90 days, a week, a calendar month or quarter, or any range: downtime, incidents, each monitor worst first, the longest incidents with their causes, and planned maintenance. Below Growth, only the sent weekly report.
suggest_monitorsReadScan a domain the way Setup does (its usual subdomains and certificates) and suggest what to monitor, marking what's already monitored. Adds nothing.
list_alertsReadWho hears about incidents: every alert with its events, where it sends them, its scope and whether it's paused, plus the connected integrations an alert can post to.
add_monitorsWriteAdd website and API checks, certificate expiry, open ports, ping, DNS and MCP server checks, up to 20 at a time, from every region your plan allows. Skips what's already monitored.
add_cron_monitorWriteWatch a scheduled job by how often it runs or its cron schedule. Returns the ping URL and the line to add to the job.
create_status_pageWriteCreate a status page showing chosen monitors. Private unless you ask for it to be public.
add_to_status_pageWriteShow more monitors on an existing status page, after the ones it shows.
add_alertWriteSend incidents to a connected Slack, Discord, Teams, Telegram or PagerDuty integration, to email addresses or to a webhook, optionally only for some tags, severities or monitors.
set_alert_pausedWriteStop an alert from sending, e.g. during planned work, or let it send again.
add_reportWriteAdd an uptime report, e.g. one per client: every monitor, chosen ones or tagged ones against an SLA target, emailed on a schedule or read on demand, optionally branded. Growth and above.
update_reportWriteChange a report's monitors, SLA target, email schedule, recipients or branding, the default report included.
create_incidentWriteOpen an incident by hand, optionally shown on status pages (which notifies their subscribers).
post_incident_updateWriteAdd an update to an incident's timeline, public or internal, move it to a new status, and show it on status pages, including incidents a monitor opened automatically. Those resolve on their own when the monitor recovers, so only incidents opened by hand can be set to Resolved.
set_monitor_pausedWritePause or resume a monitor or heartbeat.
trigger_checkWriteRun a website or API check right away from all its regions, e.g. to confirm a fix.
schedule_maintenanceWriteSchedule a maintenance window for some monitors. Their alerts and incidents are held back while it runs, and it can be announced on status pages.
follow_dependencyWriteFollow a third-party service, or some of its probes, so its outages open incidents in your workspace. Or stop following it.

Write tools act on production

Public incident updates reach your status pages and their subscribers, paused monitors stop alerting, a new alert sends the next matching incident, and a report's recipients get its next email. The server asks assistants to confirm with you before posting public updates, publishing a status page or pausing monitors, and most clients ask before running a write tool. There are no tools that delete anything.

Request headers, credentials and request bodies in a monitor's configuration are never sent to the assistant.

Things to ask

  • "Is anything down right now?"
  • "Is GitHub having problems, or is it just us?"
  • "How has the checkout API's latency looked this week, per region?"
  • "Did we meet our SLA last month? What caused the downtime?"
  • "Why did last night's incident open? Show me the failed checks."
  • "Post a public update on the open incident: the fix is deployed and we're monitoring."
  • "Schedule maintenance for the API tonight from 22:00 to 23:00 UTC."
  • "Pause the nightly backup heartbeat while I migrate the server."
  • "Set up monitoring for acme.com."
  • "Alert #ops in Slack when anything tagged prod goes down."
  • "Watch our nightly backup cron job and put it on the status page."