Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Search Errors

search_errors
Read-only

Find and analyze Sentry error events—exceptions, crashes, and stack traces—with counts, aggregates, and time trends. Use for individual events, not grouped issue lists.

Instructions

Search Sentry error events: exceptions, crashes, and stack traces, including top errors and trends over time. Returns individual events, counts, and aggregates; for grouped issue lists, use search_issues. For log lines, including error-level logs, use search_logs.

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": "search_errors"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoSort field, - prefix for descending, such as -count() for aggregates. Omit unless you need a specific order.
freshNoBypass cached reads.
limitNoMaximum number of results to return.
queryNoWhat to find, in natural language or Sentry search syntax. Put environment, release, and other filters here.
fieldsNoColumns to return; omit unless you need exact columns. Include aggregates such as count() or avg() for statistics.
periodNoRelative time window, e.g. `30m`, `24h`, `7d`, `90d`.
regionUrlNo
projectSlugNo
organizationSlugNoThe organization slug, from `find_organizations`. In `org/project` notation, the part before the slash.
includeExplanationNoExplain how the query was translated or repaired.

Output Schema

NameRequiredDescriptionDefault
urlYesOpens these results in Sentry.
notesYes
queryYes
resultsYes
resultTypeYes
timeSeriesYes
explanationYes
executedSearchYes
presentationHintYes
suggestedActionsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds the event-level granularity of results versus grouped issues, which is genuinely useful behavioral context. However, it says nothing about pagination, caching (despite a 'fresh' parameter), or result limits beyond what the schema declares, so it remains a modest supplement.

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 sentences, front-loaded with what it searches, then the result shape, then two explicit alternative-tool redirects. No filler words and nothing repeated from the schema or annotations.

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?

An output schema exists, so return values need not be explained, and the description correctly omits them. With ten parameters and zero required, an agent might still wonder whether organizationSlug/projectSlug are effectively mandatory, which the description does not address. Otherwise it is complete for this tool's complexity.

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 80%, so the schema already documents sort, fresh, limit, query, fields, period, and the slug parameters, making 3 the baseline. The description adds no parameter-level meaning — it does not explain the natural-language-vs-Sentry-syntax query behavior, how aggregates interact with fields, or that all ten parameters are optional.

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 — 'Search Sentry error events: exceptions, crashes, and stack traces' — and adds the scope of results ('top errors and trends over time'). It explicitly distinguishes itself from search_issues and search_logs, so an agent can pick the right tool 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 Guidelines5/5

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

Gives explicit routing rules: use this for individual events, counts, and aggregates; use search_issues for grouped issue lists; use search_logs for log lines, including error-level ones. The error-level-logs exclusion is especially valuable because that is the most likely mis-selection.

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