Flanj drift.flanj.io · daily contract watch

drift.flanj.io / servers / sentry

Server sheet · api · credentialed

Sentry sentry

8 change events over 51 comparison days: 0 breaking, 9 warning and 1 info findings, each with the two contracts as served behind it.

watched since 2026-08-24 as of 2026-10-15 52 days observed 51 comparison days latest snapshot 2026-10-15

01 / the server

What the watch knows about it.

https://mcp.sentry.dev/mcpendpoint
Sentryoperator
apikind
credentialedauth posture
15tools listed
52days observed
2026-07-28MCP revision · floor, not ceiling
4 / 15outputSchema declared

This server answers tools/list only with a credential attached, so its findings cannot be reproduced anonymously; the watch attaches the credential the operator documents for machine access.

02 / event timeline — every event, expanded

8 change events, newest first.

2026-10-14 → 2026-10-15 1 warning 1 tool
1 description-changedas served: 2026-10-14 → 2026-10-15on the index
warning wording description-changed The wording an agent reads to choose and call the tool changed; its behaviour may or may not have. credentialed #
search_logs description
[…] Only pass fields/sort when you need exact columns or ordering. - Sentry search syntax for logs includes RE2 regex filters, never quoted: `message://^Timeout after \d+ms//`. </hints>
as served: 2026-10-14 → 2026-10-15
2026-10-02 → 2026-10-03 2 warning 2 tools
2 description-changedas served: 2026-10-02 → 2026-10-03on the index
warning wording description-changed The wording an agent reads to choose and call the tool changed; its behaviour may or may not have. credentialed #
analyze_issue_with_seer description
[…] not support metric alert issues (issueCategory: metric); use get_issue_details and search_events search_metrics or search_traces instead - If the user provides an issueUrl, extract it […]
as served: 2026-10-02 → 2026-10-03
warning wording description-changed The wording an agent reads to choose and call the tool changed; its behaviour may or may not have. credentialed #
search_issues description
[…] environment:production - userCount:>100 DO NOT USE FOR COUNTS/AGGREGATIONS → use search_events search_errors DO NOT USE FOR individual events with timestamps → use search_events search_errors, search_logs, or search_traces DO NOT USE FOR details about a specific issue → […]
as served: 2026-10-02 → 2026-10-03
2026-10-01 → 2026-10-02 1 warning 1 tool
1 description-changedas served: 2026-10-01 → 2026-10-02on the index
warning wording description-changed The wording an agent reads to choose and call the tool changed; its behaviour may or may not have. credentialed #
search_events description
[…] lists (use search_issues) or app screenshots/images (use get_latest_base_snapshot). <examples> search_events(organizationSlug='my-org', dataset='errors', query='how many errors today') search_events(organizationSlug='my-org', dataset='errors', fields=['issue', 'count()'], sort='-count()') search_events(organizationSlug='my-org', dataset='errors', query='errors per hour last 24h') search_events(organizationSlug='my-org', dataset='spans', query='span.op:db', sort='-span.duration') search_events(organizationSlug='my-org', […]
as served: 2026-10-01 → 2026-10-02
2026-09-30 → 2026-10-01 2 warning 2 tools
2 description-changedas served: 2026-09-30 → 2026-10-01on the index
warning wording description-changed The wording an agent reads to choose and call the tool changed; its behaviour may or may not have. credentialed #
find_organizations description
[…] specific organizations by name or slug Returns up to 25 results. If you hit this limit, use results per page. When hasMore is true, pass the query parameter returned nextCursor with the same filters and scope to narrow down results. fetch the next page.
as served: 2026-09-30 → 2026-10-01
warning wording description-changed The wording an agent reads to choose and call the tool changed; its behaviour may or may not have. credentialed #
find_projects description
[…] specific projects by name or slug Returns up to 25 results. results per page. When hasMore is true, use pass the query parameter returned nextCursor with the same filters and scope to narrow down results. fetch the next page.
as served: 2026-09-30 → 2026-10-01
2026-09-18 → 2026-09-19 1 info 1 tool
1 catalog-moved-behind-meta-toolsas served: 2026-09-18 → 2026-09-19on the index
info catalog catalog-moved-behind-meta-tools The tools still exist, reached a different way. Recorded as ONE event, never as one removal per tool no longer listed. credentialed #
their contract · 2026-09-18
{"tools_listed":9}
their contract · 2026-09-19
{"completeness":"none","meta_tools":["search_sentry_tools","execute_sentry_tool"],"strategy":"none"}
as served: 2026-09-18 → 2026-09-19
2026-09-14 → 2026-09-15 1 warning 1 tool
1 description-changedas served: 2026-09-14 → 2026-09-15on the index
warning wording description-changed The wording an agent reads to choose and call the tool changed; its behaviour may or may not have. credentialed #
search_events description
Search Sentry events and replays. Use for event counts/statistics. `query` can be is natural language or Sentry search syntax. With an syntax; a configured agent configured, it fixes dataset, query, fields, and sort before running. sort. Supports TWO THREE query types: 1. AGGREGATIONS (counts, sums, averages): 'how many errors', […] 2. Individual events with timestamps: 'error logs from last hour' 3. TIME SERIES (metric over time): 'errors per hour', 'error trend over time' Datasets: - errors: Exception/crash events with stack traces, usually grouped […] (use get_latest_base_snapshot). <examples> search_events(organizationSlug='my-org', query='how many errors today') search_events(organizationSlug='my-org', dataset='errors', query='level:error') search_events(organizationSlug='my-org', dataset='errors', fields=['issue', 'count()'], sort='-count()') search_events(organizationSlug='my-org', query='errors per hour last 24h') search_events(organizationSlug='my-org', dataset='spans', query='span.op:db', sort='-span.duration') search_events(organizationSlug='my-org', dataset='replays', query='count_errors:>0', sort='-count_errors') </examples> <hints> - If the user passes a parameter in the form of name/otherName, it's likely in the format of <organizationSlug>/<projectSlug>. - Parse org/project name/otherName notation directly without calling find_organizations or find_projects. means <organizationSlug>/<projectSlug>; parse it directly, don't call find_organizations/find_projects. - Use fields with aggregate functions like count(), avg(), sum() […]
as served: 2026-09-14 → 2026-09-15
2026-09-10 → 2026-09-11 1 warning 1 tool
1 description-changedas served: 2026-09-10 → 2026-09-11on the index
warning wording description-changed The wording an agent reads to choose and call the tool changed; its behaviour may or may not have. credentialed #
update_issue description
[…] issue's status or assignment. Use this to resolve, reopen, assign, unassign, or ignore an issue. <examples> ``` update_issue(organizationSlug='my-org', issueId='PROJECT-123', status='resolved') update_issue(organizationSlug='my-org', issueId='PROJECT-123', assignedTo='user:123456') update_issue(organizationSlug='my-org', issueId='PROJECT-123', assignedTo=null) update_issue(organizationSlug='my-org', issueId='PROJECT-123', status='ignored') update_issue(organizationSlug='my-org', issueId='PROJECT-123', status='ignored', ignoreMode='forever') update_issue(organizationSlug='my-org', issueId='PROJECT-123', status='ignored', ignoreMode='untilOccurrenceCount', ignoreCount=100, […] At least one of `status` or `assignedTo` is required. - Omit `assignedTo` format: to leave assignment unchanged. Pass `null` to unassign; otherwise use `user:ID` or `team:ID_OR_SLUG`. - Use `execute_sentry_tool(name='whoami', arguments={})` to find your […]
as served: 2026-09-10 → 2026-09-11
2026-08-26 → 2026-08-27 1 warning 1 tool
1 description-changedas served: 2026-08-26 → 2026-08-27on the index
warning wording description-changed The wording an agent reads to choose and call the tool changed; its behaviour may or may not have. credentialed #
get_sentry_resource description
[…] the resource type is auto-detected. Supports issues, events, traces, spans, AI agent conversations, replays, monitors, preprod snapshots, and snapshot images. Trace lookups return a condensed overview by default. AI Agent Conversations: A conversation is a set of spans sharing the […] to fetch the transcript/details. To discover or list conversations, use search_ai_conversations. search_agent_conversations. Conversations are NOT issues — do not use search_issues for […]
as served: 2026-08-26 → 2026-08-27

03 / tool inventory · as served on 2026-10-15

15 tools in the latest contract.

From the snapshot as served; descriptions shortened to their first sentence. “Changes” counts this server’s findings on the tool.

Tools in the latest snapshot with their input property counts, outputSchema declaration and finding counts
ToolDescriptionInputsRequiredoutputSchemaAnnotationsChanges
analyze_issue_with_seer Use Seer to analyze production errors and get detailed root cause analysis with specific code fixes. 5 0 none openWorld 1
execute_sentry_tool Execute an available Sentry MCP tool discovered through search_sentry_tools. 2 1 none destructive · openWorld 0
find_dropped_events Find events dropped before they were stored in Sentry — ground-truth data-fidelity information about what was and wasn't captured. 10 1 declared readOnly · openWorld 0
find_organizations Find organizations that the user has access to in Sentry. 2 0 declared readOnly · openWorld 1
find_projects Find projects in Sentry. 4 1 declared readOnly · openWorld 1
get_sentry_resource Fetch a Sentry resource by URL, or by resourceType plus resourceId. 4 0 none readOnly · openWorld 1
search_errors Search Sentry error events: exceptions and crashes with stack traces. 9 1 none readOnly · openWorld 0
search_issues Search for grouped issues/problems in Sentry - returns a LIST of issues, NOT counts or aggregations. 8 1 none readOnly · openWorld 1
search_logs Search Sentry logs: application log entries, including error- and warning-severity log messages. 9 1 none readOnly · openWorld 1
search_metrics Search Sentry metrics: counters, gauges, and distributions, as rows or aggregates. 9 1 none readOnly · openWorld 0
search_profiles Search Sentry profiles: transaction and continuous profile results, profile IDs, and profiled transactions. 9 1 none readOnly · openWorld 0
search_replays Search Sentry session replays: rage clicks, dead clicks, visited pages, errors seen, and replay users. 9 1 none readOnly · openWorld 0
search_sentry_tools Search the available Sentry MCP tool catalog by name and description. 2 1 declared readOnly 0
search_traces Search Sentry spans and traces: requests, API/HTTP calls, endpoints, DB queries, AI/LLM calls, and other operations. 9 1 none readOnly · openWorld 0
update_issue Update a Sentry issue's status or assignment. 13 0 none destructive · openWorld 1