Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Search Replays

search_replays
Read-only

Find Sentry session replays by rage clicks, dead clicks, visited pages, errors, or users to inspect user behavior; returns replay lists rather than counts or aggregates.

Instructions

Search Sentry session replays by rage clicks, dead clicks, visited pages, errors seen, and users. Returns replay lists, not counts or aggregates.

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_replays"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoReplay sort, - prefix for descending: -started_at (default), -count_errors, -count_rage_clicks, or -duration.
freshNoBypass cached reads.
limitNoMaximum number of results to return.
queryNoWhat to find, in natural language or replay search syntax such as count_errors:>0 or url:*checkout*.
periodNoRelative time window, e.g. `30m`, `24h`, `7d`, `90d`.
regionUrlNo
environmentNoEnvironment name or list of names.
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
replaysYes
explanationYes
executedSearchYes
presentationHintYes
suggestedActionsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, establishing the safe-read profile. The description adds the important constraint that results are replay lists rather than counts or aggregates, but says nothing about pagination, the effect of the `fresh` cache-bypass flag, or result volume/limits.

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, with the searchable dimensions front-loaded and the output-shape caveat immediately after. Every clause carries information an agent can act on.

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 described, and annotations cover the safety profile; with 10 parameters at 80% coverage, the definition is complete enough to call correctly. Minor gaps remain around pagination/limits and when to prefer this over sibling search tools.

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 query syntax, sort options, period format, and org/project slug derivation. The description's enumeration of filter dimensions (rage clicks, dead clicks, visited pages, errors seen, users) loosely maps to the `query` parameter but adds no syntax or format detail beyond what the schema provides; baseline 3 applies.

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 session replays") and enumerates the searchable dimensions (rage clicks, dead clicks, visited pages, errors seen, users). The closing clause "Returns replay lists, not counts or aggregates" pins down the output shape, so the agent can distinguish this from the aggregate/search siblings on the replay resource without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

The "not counts or aggregates" clause functions as a soft when-not, steering agents away from expecting totals. However, there is no positive usage guidance (e.g. prerequisites like organization/project slug, or when to prefer this over search_errors or search_issue_events) and no named alternative for aggregate needs.

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