Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Create Uptime Monitor

create_uptime_monitor

Create a Sentry uptime monitor that checks a URL over HTTP at a set interval, with configurable method, timeout, thresholds, and status to detect downtime.

Instructions

Create a Sentry uptime monitor that checks a URL over HTTP on an interval. Response assertions are not supported; set them in the Sentry UI. Scheduled jobs (cron): find_monitors. Metric thresholds: find_metric_monitors.

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": {
      "projectSlug": "<projectSlug>",
      "name": "<name>",
      "url": "<url>",
      "intervalSeconds": "<intervalSeconds>"
    },
    "name": "create_uptime_monitor"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesURL to check (max 255 characters).
bodyNoRequest body, for methods that take one.
nameYesMonitor display name.
ownerNoOwner as `user:ID` or `team:ID`.
methodNoHTTP method used for the uptime check request.
statusNoMonitor status. `disabled` stops checks and does not count against quota.
headersNoHTTP headers as [name, value] pairs, e.g. [["Accept","application/json"]].
regionUrlNo
timeoutMsNoRequest timeout in milliseconds.
environmentNoEnvironment for uptime issues this monitor creates.
projectSlugYesThe project slug. In `org/project` notation, the part after the slash.
traceSamplingNoWhether check requests may be considered for tracing.
intervalSecondsYesSeconds between checks: 60, 300, 600, 1200, 1800, or 3600.
organizationSlugNoThe organization slug, from `find_organizations`. In `org/project` notation, the part before the slash.
downtimeThresholdNoConsecutive failed checks required to mark down.
recoveryThresholdNoConsecutive successful checks required to recover.
responseCaptureEnabledNoCapture response body and headers on failed checks.

Output Schema

NameRequiredDescriptionDefault
monitorYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the mutation and external-request profile is covered structurally. The description adds a genuine functional limitation not present in the schema – no response assertions – which prevents a class of failed expectations. It says nothing about permissions, quota impact, or whether checks begin immediately on creation.

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

Conciseness4/5

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

Two sentences, front-loaded with the core action, with zero filler. The second sentence is telegraphic ('Scheduled jobs (cron): find_monitors') and slightly terse to parse, but it is not wasteful.

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 17-parameter creation tool, the description supplies purpose, a key limitation, and sibling routing, while the rich input schema and an existing output schema cover field semantics and return values. Missing pieces such as auth requirements or quota effects are modest gaps rather than blockers.

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 94%, so nearly every one of the 17 parameters is already documented (allowed interval values, header pair format, owner patterns, thresholds). The description adds no parameter-level meaning beyond the URL/interval framing, so the baseline 3 applies.

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 (create), a specific resource (Sentry uptime monitor) and the mechanism (checks a URL over HTTP on an interval), which is clearly distinct from its siblings. It does not explicitly name the create-side alternatives (create_monitor for cron, create_metric_monitor for thresholds), instead pointing at the find_ counterparts, so differentiation is slightly indirect.

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 an explicit exclusion (response assertions are not supported; set them in the Sentry UI) and routes two adjacent use cases elsewhere (cron via find_monitors, metric thresholds via find_metric_monitors). It stops short of telling the agent which create tool to pick for those use cases, but the when-not-to-use guidance is concrete.

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