Skip to main content
Glama
mcp-uptime-kuma

mcp-uptime-kuma

Update Settings

updateSettings
DestructiveIdempotent

Change Uptime Kuma server settings by sending only the values to modify; unspecified settings keep stored values, and the saved settings are returned.

Instructions

Changes Uptime Kuma server settings. Pass only what should change; every other setting keeps its stored value. Returns the settings as saved. Turning login off (disableAuth: true) needs currentPassword and leaves the dashboard open to anyone who can reach it. Read the current values with getSettings.

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": "updateSettings"
  }
}

Input Schema

NameRequiredDescriptionDefault
nscdNoCache DNS lookups with NSCD (Docker images only)
entryPageNoWhat "/" opens: "dashboard", or a status page as "statusPage-<slug>". Find slugs with listStatusPages.
apiEnabledNoThe "API" switch in Settings > General
trustProxyNoTrust X-Forwarded-* headers. Set only when Uptime Kuma sits behind a reverse proxy.
checkUpdateNoShow when a new Uptime Kuma version is available
disableAuthNotrue turns login off: anyone who can reach Uptime Kuma gets full control. Needs currentPassword. false turns login back on and logs out every other session.
steamAPIKeyNoSteam Web API key, used by Steam game server monitors. A credential: "***" (what read tools return) keeps the stored key, "" clears it.
includeSecretsNoReturn credentials in full instead of "***"; they then stay in the transcript. Default: false, or UPTIME_KUMA_INCLUDE_SECRETS.
primaryBaseURLNoThe public address of this Uptime Kuma, used for links in notifications, e.g. "https://status.example.com". "" clears it.
serverTimezoneNoIANA timezone the server shows times and schedules maintenance in, e.g. "America/Edmonton" or "UTC"
currentPasswordNoThe admin password. Required only to turn login off (disableAuth: true) while it is on; never stored or returned.
chromeExecutableNoPath of the Chrome or Chromium binary real-browser monitors run, e.g. "/usr/bin/chromium". "" auto-detects. Changing it restarts the browser.
searchEngineIndexNoLet search engines index status pages
globalpingApiTokenNoGlobalping API token, used by globalping monitors. A credential: "***" (what read tools return) keeps the stored token, "" clears it.
keepDataPeriodDaysNoDays of heartbeat history to keep; older beats are deleted
tlsExpiryNotifyDaysNoDays before a TLS certificate expires to send a warning, e.g. [7, 14, 21]. Replaces the whole list.
prometheusApiEnabledNoCollect Prometheus metrics. Changing it starts or stops the collection.
domainExpiryNotifyDaysNoDays before a domain registration expires to send a warning. Replaces the whole list.

Output Schema

NameRequiredDescriptionDefault
okYes
msgNo
changedYesThe settings this call changed
settingsYesUptime Kuma server settings after the change

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 destructiveHint=true, idempotentHint=true, and readOnlyHint=false; the description goes beyond them by disclosing patch semantics, the cheap-but-dangerous auth toggle, that disabling auth logs out other sessions and opens the dashboard publicly, and that changing chromeExecutable restarts the browser. What keeps it from a 5 is that return behavior ("Returns the settings as saved") lightly duplicates the output schema rather than adding new detail.

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?

Five short sentences, front-loaded with the update contract, then risk, then a pointer to the read tool. Every sentence carries actionable information, and none of the 18 parameters is enumerated redundantly.

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 an 18-parameter mutation tool with full schema and output-schema coverage, the definition supplies the operations contract, the destructive caveat, and the cross-tool read path — enough to call it correctly. It doesn't discuss error behavior on an invalid currentPassword, which is the only notable practical gap.

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

Parameters3/5

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

Schema description coverage is 100%, so each of the 18 parameters is already documented in the schema, including the currentPassword-required-for-disableAuth dependency and the "***" credential round-trip. The description restates those same rules at a high level instead of adding syntax or edge cases, so the baseline 3 applies.

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?

States a specific verb and resource ("Changes Uptime Kuma server settings") and immediately adds the partial-update scope ("Pass only what should change"). It also names the read counterpart, getSettings, so an agent can distinguish this from the sibling without inspecting schemas.

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

Usage Guidelines5/5

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

Gives explicit when-to-use direction ("Read the current values with getSettings" before mutating) and states the operating contract (only supplied fields change). It also flags the highest-risk path — turning login off — with the precondition attached, leaving little to inference.

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