Skip to main content
Glama
mcp-uptime-kuma

mcp-uptime-kuma

Create Maintenance Window

createMaintenanceWindow

Schedules maintenance windows so selected Uptime Kuma monitors report MAINTENANCE instead of DOWN and suppress alerts during planned downtime.

Instructions

Schedules a new maintenance window: while it is in effect the monitors in monitorIDs show MAINTENANCE instead of DOWN and do not alert. A window without monitorIDs suppresses nothing. strategy sets the schedule; "manual" makes a window you switch on and off with setMaintenanceWindowActive. To stop one monitor's checks outright use setMonitorActive.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "title": "<title>",
      "strategy": "<strategy>"
    },
    "name": "createMaintenanceWindow"
  }
}

Input Schema

NameRequiredDescriptionDefault
cronNoCron expression for when the window starts, e.g. "30 3 * * *" (03:30 daily), for the cron strategy
titleYesTitle of the maintenance window
activeNoWhether the window is active (default: true). For a manual window, active means in maintenance right now.
strategyYesScheduling strategy: single=one-time, recurring-interval=every N days, recurring-weekday=specific weekdays, recurring-day-of-month=specific dates, cron=starts on a cron expression and lasts durationMinutes, manual=on whenever active
timezoneNoTimezone the dates and times are in (e.g. "America/New_York", "UTC"). Omit to follow the server timezone.
weekdaysNoDays of week (0=Sunday … 6=Saturday) for recurring-weekday strategy
dateRangeNo[start, end] as local times in the window's timezone, e.g. ["2026-10-08T10:00", "2026-10-08T12:00"]. Required for single; optional bounds for recurring strategies; ignored for manual.
timeRangeNoDaily [{hours, minutes}, {hours, minutes}] start and end. Required for the recurring-* strategies, ignored otherwise.
monitorIDsNoIDs of the monitors this window suppresses. A window with no monitors suppresses nothing. On update this REPLACES the current list; pass [] to detach all.
daysOfMonthNoDays of month (1-31) for recurring-day-of-month strategy
descriptionNoDescription or reason for the maintenance
intervalDayNoInterval in days for recurring-interval strategy
durationMinutesNoHow long each window lasts, in minutes, for the cron strategy
statusPageSlugsNoSlugs of the status pages that announce this window while it is in effect. On update this REPLACES the current list; pass [] to remove it from all. Find slugs with listStatusPages.

Output Schema

NameRequiredDescriptionDefault
okYes
msgNo
monitorIDsNo
maintenanceIDNo
statusPageSlugsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.17.0

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this is a non-read-only, non-destructive, non-idempotent write, and the description adds real behavioral context: the window's effect on monitor state and alerting, and the important footgun that a window without monitorIDs suppresses nothing. It does not address duplicate creation (relevant given idempotentHint=false) or permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, each carrying distinct information: what it does, the empty-monitorIDs caveat, and the strategy/alternative routing. No repetition of the title and nothing that could be cut without losing meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 14-parameter write tool with an output schema and full schema descriptions, the description covers purpose, effect, and the key scoping caveat, which is enough to call it correctly. It leaves out permission prerequisites and duplicate-creation behavior, the main remaining gaps for a non-idempotent create.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description earns an extra point by explaining the strategy grouping in prose and tying "manual" to the active flag and to setMaintenanceWindowActive. The monitorIDs suppression semantics are reinforced rather than newly revealed, since the schema already documents them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource ("Schedules a new maintenance window") and immediately states its effect on monitors ("show MAINTENANCE instead of DOWN and do not alert"). It also distinguishes itself from two siblings by name, setMaintenanceWindowActive and setMonitorActive, so an agent can route correctly without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a concrete when-not: for taking a single monitor's checks down entirely, use setMonitorActive instead. It also explains that a manual-strategy window is toggled via setMaintenanceWindowActive, which clarifies how creation relates to that sibling. It stops short of stating prerequisites (permissions) or when to prefer updateMaintenanceWindow over creating a second window.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.