briefkin

Monitoring · 5 skills

Sentry MCP and Claude skills

Pull new and regressed issues, error counts, affected users and crash-free rates from Sentry, and report what broke since yesterday.

Connect Sentry to your agent (MCP)

  1. Sentry MCP server, Sentry's official remote server at https://mcp.sentry.dev/mcp, signed in with OAuth. Add Sentry from Claude's connector directory, or run claude mcp add --transport http sentry https://mcp.sentry.dev/mcp. It searches issues and events and pulls stack traces.
  2. sentry-cli. Mostly a release and source map tool, but sentry-cli issues list --project <slug> lists issues when a quick terminal check is enough.
  3. API with an auth token. Create an organization or personal token, store it in SENTRY_AUTH_TOKEN with SENTRY_ORG, and grant org:read, project:read and event:read.

Those three read scopes cover every report here; leave out event:write, which lets a token resolve and assign issues.

5 Sentry skills

Sentry new errors digest

Every morning: unresolved Sentry issues first seen in the last 24 hours, ranked by users and events, with the release and code they started in.

DevelopersEvery day at 8:00Report cardUses Sentry.

Sentry crash-free sessions for the latest release

Every 4 hours: the crash-free session rate of your newest release next to the previous one, with adoption, so an early number is read with care.

DevelopersEvery 4 hoursStat tileUses Sentry.

Sentry top issues by users affected

Every Monday: the 10 unresolved Sentry issues that affected the most users in the last 7 days, with owner and whether each is rising or falling.

DevelopersMondays at 8:30Report cardUses Sentry.

GitHub, Vercel and Sentry release health check

An hour after each production deploy: errors after the release against the hour before, new Sentry issues, key page checks, and the PRs that shipped.

DevelopersEvery hourReport cardUses GitHub, Vercel, Sentry.

Deploy to error to conversion chain

Each morning and after a deploy: every production release lined up with the Sentry issues it introduced and the key event rate before and after it.

DevelopersDaily at 8:00, and after each deployReport cardUses GitHub, Sentry, PostHog, Google Analytics, Vercel.

What agents do with Sentry

Sentry's API returns issues per organization or project with the same search syntax as the Issues page: is:unresolved firstSeen:-24h, is:regressed, level:error, release:1.4.2, environment:production. Each issue has count, userCount, firstSeen, lastSeen, culprit, level and a permalink, and its latest event holds the stack trace. Release health comes from the sessions endpoint (GET /api/0/organizations/{org}/sessions/ with field=crash_free_rate(session)), and alert rules and their incidents can be read too.

Developers and on-call leads schedule new errors from the last 24 hours ranked by users affected, regressions after a deploy, crash-free sessions and users for the current release, and a weekly list of the noisiest unresolved issues.

sentry.io

Often used with Sentry

Teams that use these

Your Sentry numbers, on one board with everything else

Skills are free to use with any agent. Briefkin is where their results land: one board for every report, number and question your agents send, with a ping when something needs you.

Join the open betaBrowse all skills

Free during the open beta. No card.