Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Get Sentry Resource

get_sentry_resource
Read-only

Fetch Sentry issues, events, traces, replays, monitors, dashboards, snapshots, or conversations by URL or ID; the resource type is detected from the URL.

Instructions

Fetch a Sentry resource by URL or ID: issues, events, traces, spans, agent conversations, replays, monitors, metric alerts, dashboards, preprod snapshots, and snapshot images. Start here for any Sentry URL or issue, event, trace, or replay ID; the type is detected from the URL. To list agent conversations, use search_agent_conversations.

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_sentry_resource"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNo
urlNoA Sentry URL. The resource type is detected from it.
freshNoBypass cached reads.
issueIdNo
issueUrlNo
resourceIdNoThe ID for the resource type: issue short ID (e.g. `PROJECT-123`), event, trace, replay, or conversation ID, monitor slug, dashboard ID or exact title, or snapshot artifact ID. Required without a URL.
resourceUrlNo
packageNamesNoExact, case-sensitive package names recorded on the event. Returns their versions. Only for an event URL or the `event` type.
resourceTypeNoRequired without a URL. With a URL, `trace` widens a span URL to its whole trace. `ai_conversation` is a gen_ai.conversation.id; `snapshot` is a preprod snapshot.
organizationSlugNoThe organization slug, from `find_organizations`. In `org/project` notation, the part before the slash.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the resource type is inferred from the URL, and span URLs can be widened to a whole trace. It stops short of saying what a fetch returns or what happens when the type cannot be detected.

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?

Front-loaded with the verb and the accepted types, then the routing rule, then the alternative — a sensible order. The long type enumeration costs some length, but each entry maps to a supported resourceType value rather than being filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 10 parameters, zero required fields, and no output schema, the description leaves the hardest question open: which of the many ID/URL aliases to supply and how they interact. Type detection from the URL is covered, but the parameter-selection logic for the non-URL path is not, which is a meaningful gap for a tool this flexible.

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 60%, so several fields (id, issueId, issueUrl, resourceId, resourceUrl) are left for the schema to explain. The description's 'the type is detected from the URL' clarifies url behavior and its type enumeration maps onto resourceType, but it adds nothing about the duplicate ID/URL aliases, packageNames, organizationSlug, or fresh.

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 ('Fetch') and resource ('Sentry resource') and enumerates the accepted resource types — issues, events, traces, spans, conversations, replays, monitors, metric alerts, dashboards, preprod snapshots, snapshot images. It also names the sibling it is not ('search_agent_conversations'), so the agent can distinguish it without opening a 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?

'Start here for any Sentry URL or issue, event, trace, or replay ID' gives an explicit entry-point rule, and the final sentence routes listing of conversations to a named alternative. It does not address overlap with the many sibling detail-getters (get_issue_details, get_trace_details, get_replay_details, get_dashboard_details), so an agent still has to infer which one wins on an ID-only call.

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