Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Search Agent Conversations

search_agent_conversations
Read-only

Search and filter LLM agent conversations by query, time, project, or environment to view summaries with cost, token, call-count, and preview data.

Instructions

Search Sentry agent conversations (formerly AI conversations): one summary row per LLM agent conversation with title, cost, tokens, call counts, and previews. For one conversation's transcript, use get_agent_conversation_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": "search_agent_conversations"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoEnd of the search window; requires start.
freshNoBypass cached reads.
limitNo
queryNoSearch filter for conversations.
startNoStart of the search window; requires end and overrides period.
cursorNoPagination cursor from a previous response.
periodNoRelative time window, e.g. `30m`, `24h`, `7d`, `90d`.30d
projectNoProject slug or numeric project ID, or an array of projects.
regionUrlNoThe organization's region URL from `find_organizations`, e.g. `https://us.sentry.io`. Omit for self-hosted Sentry.
environmentNoEnvironment name, or an array of environments.
organizationSlugNoThe organization slug, from `find_organizations`. In `org/project` notation, the part before the slash.

Output Schema

NameRequiredDescriptionDefault
countYes
searchUrlYes
nextCursorYes
conversationsYes
organizationSlugYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A4/5.0
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 useful behavioral context by saying results are summary rows with title, cost, token, and call-count fields. It does not mention pagination behavior (the cursor param), result caps, or ordering, which would be the remaining value-adds beyond the annotations.

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, both front-loaded with the essential information: what is returned first, then the alternative. No filler, no repetition of the title, and the sibling redirect is placed where it is most actionable.

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?

Eleven parameters, an output schema, and annotations mean the description does not need to carry parameter or return-value detail. It covers purpose, return granularity, and the sibling alternative. A brief note on pagination across the cursor parameter is the only meaningful gap.

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 91%, so the schema already explains start/end, period format, cursor, project, regionUrl, and organizationSlug. The description adds no parameter-level meaning beyond that, which is acceptable at this coverage level but earns only the baseline.

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?

Uses a specific verb and resource ("Search Sentry agent conversations") and goes further to describe the result shape: one summary row per conversation with title, cost, tokens, call counts, and previews. It also names the sibling get_agent_conversation_details and the exact distinction (summary rows vs. one transcript), so an agent can separate the two 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 explicit routing guidance: for a single conversation's transcript, use get_agent_conversation_details. That covers the main alternative in the sibling set. It stops short of stating when not to use this tool more broadly (e.g., that it is list/search only and cannot mutate), but the positive guidance is clear.

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