Skip to main content
Glama
mcp-uptime-kuma

mcp-uptime-kuma

List Maintenance Windows

listMaintenanceWindows
Read-only

List maintenance windows with schedules, active status, affected monitors, and status pages; filter by title keywords or status to find IDs for updating, activating, or deleting windows.

Instructions

Returns every maintenance window with its schedule, whether it is active, monitorIDs (the monitors it suppresses) and statusPageSlugs (the status pages that announce it). A window with an empty monitorIDs list suppresses nothing. Use it to find the ID that updateMaintenanceWindow, setMaintenanceWindowActive and deleteMaintenanceWindow take; fields returns only the fields you name. Filter by keywords in the title, or by status, e.g. "scheduled,under-maintenance" to leave out ended windows. Returns up to 50 windows per call; pass nextCursor back as cursor for the next page.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "listMaintenanceWindows"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many windows to return (default: 50)
cursorNoThe nextCursor of the previous call, for the next page
fieldsNoOnly these fields, comma-separated, e.g. "title,active,monitorIDs"; id is always returned. Default: every field.
statusNoOnly windows in these statuses, comma-separated: inactive, scheduled, under-maintenance, ended, unknown
keywordsNoSpace-separated keywords matched against the window's title, case-insensitively; all must match

Output Schema

NameRequiredDescriptionDefault
countYesHow many windows this page holds
totalYesHow many match the filters, across every page
nextCursorNoPass as cursor for the next page; absent on the last page
maintenanceWindowsYesArray of maintenance windows; with fields, only the fields asked for

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.17.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare it is a safe, closed read; the description adds real behavioral detail beyond them: page size cap ('up to 50 windows per call'), the cursor round-trip, field projection semantics ('fields returns only the fields you name'), and the edge case that an empty monitorIDs list suppresses nothing.

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?

Return shape comes first, followed by purpose, filtering, and pagination in that order. Despite being multi-sentence, every clause carries distinct information (empty-list semantics, cursor reuse, projection) with no filler.

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

Completeness5/5

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

Even though an output schema exists, the description tells the agent how paging terminates and how to control payload size, which are the practical risks for an unbounded list call. Nothing needed to invoke it correctly is missing.

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 still adds meaning by showing how status values compose ('scheduled,under-maintenance') and clarifying that keywords match titles case-insensitively with all terms required. It reinforces rather than fully re-derives the schema.

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?

The description uses a specific verb and resource ('Returns every maintenance window') and immediately enumerates what each result carries: schedule, active flag, monitorIDs, statusPageSlugs. It is unmistakably the read/list counterpart to the create/update/delete/set-active siblings named in the text.

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?

It gives a concrete usage motive ('Use it to find the ID that updateMaintenanceWindow, setMaintenanceWindowActive and deleteMaintenanceWindow take') and explains the status filter use case ('to leave out ended windows'). It stops short of explicit exclusion guidance, but the intended workflow and filter rationale are clear.

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