Skip to main content
Glama

mcp-uptimerobot__list-incidents

Read-onlyIdempotent

List all incidents for the authenticated user with optional date range, monitor, type and root-cause filtering. type and cause filter only the newest 10,000 incidents of the timeRange, so on an account with more incidents than that, older matches are missing and totalCount is too low: narrow timeRange to reach them. Through Royally: its server marks it read-only, so it runs straight away.

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": "mcp-uptimerobot__list-incidents"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoFilter incidents by type: "Downtime", "SlowResponse" or "VisualChange". The output shows these in `type` as "Downtime", "Slow Response" and "Visual Change"; pass the value without the space.
causeNoFilter incidents by root cause group, matched against the numeric `cause` in the output: "2xx", "3xx", "4xx", "5xx" (HTTP status 200-299, 300-399, 400-499, 500-599), "Timeout" (333333), "DNS" (100001 and 222222), "AssertionFailed" (777777), "InvalidJSON" (700003), "ConfigError" (700002). Combines with type by AND.
limitNoNumber of items to return per page (default: 10, max: 100)
cursorNoPagination cursor for next page (incident ID)
statusNoFilter incidents by status. "open" returns only currently ongoing incidents, regardless of timeRange, so an outage that started months ago is still returned.
site_idNoSite to run this tool on: 0b6d9b21-ca64-4476-bc68-d1cd935ca7cb (https://mcp.uptimerobot.com/mcp)
monitorIdNoFilter incidents to only those belonging to this monitor ID. Must be a positive integer representing a monitor owned by the authenticated user.
timeRangeNoTime range for data retrieval. Relative format: "1h" to "90d" (e.g., "24h", "7d"). Absolute format: ISO 8601 interval "startDate/endDate" (e.g., "2024-01-01T00:00:00Z/2024-01-31T23:59:59Z"). Defaults to "7d" (last 7 days). Ignored when status is "open": an ongoing incident is returned whatever its start date.7d

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

The 10,000-incident cap on type/cause filtering, its understated totalCount, and the remedy (narrow timeRange) are genuine behavioral disclosures that annotations cannot convey and that materially affect result trustworthiness. The closing sentence about read-only execution largely restates readOnlyHint, adding little beyond the annotations.

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

Conciseness3/5

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

The truncation caveat is well placed and earns its space, but the final sentence about the server marking it read-only duplicates the annotations and is awkwardly worded. Three sentences are otherwise tight, though initial filter enumeration repeats the schema.

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?

Covers the non-obvious risks for an 8-parameter list tool: filter truncation, the totalCount caveat, and status='open' ignoring timeRange (in schema). With no output schema, the description could do more to describe the returned shape or how totalCount and cursor relate, and it omits sibling differentiation.

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 description coverage is 100%, so per-parameter meaning is already baseline 3. The description nevertheless adds cross-parameter semantics absent from the schema: type and cause are ANDed, applied only to the newest 10,000 incidents in timeRange, and can understate totalCount. It says nothing extra about limit/cursor pagination beyond the already-documented schema.

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

Purpose4/5

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

States a specific verb and resource ('List all incidents') plus scope ('for the authenticated user') and enumerates the optional filters, so the agent knows exactly what it retrieves. It never distinguishes itself from near-neighbors such as get-incident-details or list-third-party-service-incidents, so an agent must infer the boundary from names alone.

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

Usage Guidelines3/5

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

Gives real operational guidance for one scenario: narrowing timeRange to reach matches that type/cause truncation hides. It also notes the call runs without confirmation. But it offers no explicit when-to-use/when-not guidance against sibling incident tools (e.g., details vs. list vs. activity log), leaving that mapping to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources