Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Get Transaction Profile

get_profile
Read-only

Analyze aggregated CPU profiles for one Sentry transaction to surface hot paths, per-function p75/p95/p99 latency, user vs library code, and regressions against a baseline period.

Instructions

Analyze aggregated CPU profiles (flamegraph) for one Sentry transaction: hot paths, per-function p75/p95/p99, user versus library code, and regressions against a baseline period. For one profile by ID or URL, use get_profile_details.

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": "get_profile"
  }
}

Input Schema

NameRequiredDescriptionDefault
freshNoBypass cached reads.
periodNoRelative time window, e.g. `30m`, `24h`, `7d`, `90d`.7d
regionUrlNo
profileUrlNoSentry profile URL; the organization and project come from it. transactionName is still required.
maxHotPathsNoNumber of hot paths to show.
focusOnUserCodeNoShow only application code; false includes library code.
projectSlugOrIdNoProject slug or numeric ID; required unless profileUrl has it.
transactionNameNoExact, case-sensitive transaction name, such as /api/users or POST /graphql. Required; find names with search_traces.
organizationSlugNoThe organization slug, from `find_organizations`. In `org/project` notation, the part before the slash.
compareAgainstPeriodNoBaseline time window to compare against, for regression detection.

Output Schema

NameRequiredDescriptionDefault
periodYes
analysisYesSingle-period analysis. Null when comparing or without data.
guidanceNo
projectIdYes
comparisonYesBaseline comparison. Null unless both periods have data.
baselinePeriodYesNull unless compareAgainstPeriod was set.
hasCurrentDataYes
focusOnUserCodeYes
hasBaselineDataYesNull unless compareAgainstPeriod was set.
transactionNameYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A4.2/5.0
Behavior4/5

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 real behavioral context beyond that: results are aggregated over a time window, percentiles are computed per function, user code is filtered by default, and regressions are computed against a baseline period. It does not mention the caching behavior implied by the 'fresh' parameter or relative cost of the aggregation, which keeps it from a 5.

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?

Two sentences, zero filler, and the primary purpose plus the returned dimensions are front-loaded before the disambiguation clause. Every clause carries information an agent needs either to select or to interpret the tool.

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 ten-parameter tool with a 90% described schema, full annotations, and an output schema, the description covers the essential selection and interpretation context. The remaining gaps are small: it does not flag the required transactionName or the 7d default period, but the schema handles both, and output shape is covered by the output schema.

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 90%, so the schema already documents all ten parameters with examples and defaults, and the baseline of 3 applies. The description echoes a few of them conceptually ('hot paths', 'user versus library code', 'regressions against a baseline period') but adds no syntax, format, or constraint details beyond what the schema states. It also never mentions that transactionName is required.

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 ('Analyze aggregated CPU profiles (flamegraph) for one Sentry transaction') and enumerates the dimensions returned: hot paths, per-function p75/p95/p99, user versus library code, and regressions against a baseline. It also names the sibling it is not, so an agent can separate it from get_profile_details without opening either schema.

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 routing rule: 'For one profile by ID or URL, use get_profile_details.' That is a genuine when-not with a named alternative tied to a distinguishing condition. It stops short of a full decision guide (e.g., when to reach for this instead of get_trace_details or search_traces when hunting regressions), so it is strong but not exhaustive.

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