Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Get Profile Details

get_profile_details
Read-only

Inspect a single Sentry transaction or continuous profile by ID, profiler ID, or URL to view trace, release, runtime, sample, thread, and top-frame details.

Instructions

Inspect one Sentry profile by profile ID, profiler ID, or URL: transaction, trace, release, and runtime details, sample and thread structure, and top frames. Handles transaction and continuous profiles. For aggregated hot paths across a transaction, use get_profile.

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_details"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoContinuous profile window end, ISO 8601; only with profilerId.
freshNoBypass cached reads.
startNoContinuous profile window start, ISO 8601 such as 2024-01-01T00:00:00Z; only with profilerId.
profileIdNoTransaction profile ID. Do not combine with profilerId.
regionUrlNo
profileUrlNoSentry transaction or continuous profile URL; the organization, project, and profile IDs come from it.
profilerIdNoContinuous profiler session ID; requires start and end.
focusOnUserCodeNoShow only application frames in the hotspot table; false includes library frames.
projectSlugOrIdNoProject slug or numeric ID; required without profileUrl.
organizationSlugNoThe organization slug, from `find_organizations`. In `org/project` notation, the part before the slash.

Output Schema

NameRequiredDescriptionDefault
profileYes
samplesYesNull for legacy profiles, which have no sample-format data.
suggestedActionsYes

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?

The annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so safety is covered. The description adds behavior beyond them: that a single profile is inspected and that both transaction and continuous profile types are handled, which changes which parameters are relevant. It says nothing further about freshness/caching semantics or response shape, but those are handled by the schema and output schema.

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, each earning its place: purpose and returned data first, then supported profile types, then the sibling routing rule. Front-loaded and free of filler or repetition of schema content.

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?

With an output schema present, the description need not explain return values, and it gives enough on modes and alternatives for a 10-parameter read-only tool. The only gap is that the transaction-vs-continuous decision point and precedence when multiple identifiers are supplied are left entirely to the 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 explains profileId vs. profilerId exclusivity, the start/end requirement for continuous profiles, and how profileUrl derives org/project. The description only restates the identifier set at a high level and adds no syntax, mutual-exclusion, or default-behavior detail beyond what the schema provides.

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?

The description opens with a specific verb and resource ('Inspect one Sentry profile') and enumerates both the accepted identifiers (profile ID, profiler ID, URL) and the returned content (transaction, trace, release, runtime, sample/thread structure, top frames). It also explicitly separates itself from the sibling that aggregates data, so an agent can route 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?

It gives a clear when-to-use-elsewhere rule: 'For aggregated hot paths across a transaction, use get_profile,' and signals that both transaction and continuous profiles are covered. What it does not state is the condition for choosing between the two modes (the transaction vs. continuous selection criteria live only in the schema's parameter descriptions).

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