Skip to content
Back to skills

Sentry

ASecurity

Use this connector skill whenever the user asks an agent to work with Sentry organizations, projects, issues, error triage, exception investigation, issue status changes, or production incident summaries.

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 19, 2026
ai-agentsbashapi

Works with

  • cli
  • api
  • mcp

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned October 19, 2026

npx -y skills add ibrdot/swe-re-expert --skill sentry --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Sentry?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Sentry
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ibrdot-sentry/badge)](https://www.skillsdirectory.com/skills/ibrdot-sentry)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: sentry
description: Use this connector skill whenever the user asks an agent to work with Sentry organizations, projects, issues, error triage, exception investigation, issue status changes, or production incident summaries.
---

# Sentry

Use Sentry through the official `sentry` MCP server. Provider credentials stay server-side; do not handle raw Sentry OAuth tokens.

## Discovery

Start from the live MCP tool descriptions:

```bash
connector-cli mcp list-servers
connector-cli mcp describe-server sentry
connector-cli mcp describe-tools sentry <tool-name>
```

Use only MCP tools returned by `describe-server`. Do not invent Sentry API parameters from upstream docs.

## Invocation

```bash
connector-cli mcp call-tool sentry <tool-name> --input '<json>'
```

`APP_SERVER_URL` must be available, and connector broker auth must come from the runtime config file or the `SANDBOX_TOKEN` local fallback. Do not print or persist `SANDBOX_TOKEN`.

## Key Rules

- Use exact Sentry organization slugs and issue IDs. If the organization slug is unknown, discover organizations with the tools exposed by the MCP server first.
- Resolve projects before filtering issue or event queries by project.
- Keep provider facts separate from incident analysis. Label root-cause or ownership statements as inference unless verified from issue metadata, stack frames, or linked code.
- Before write operations such as status or assignment changes, confirm the target issue and intended change.
- Do not claim a write succeeded until the MCP tool result confirms it.

## Workflows

**Issue triage:** List issues with the narrowest project, environment, query, and time filters available. Summarize title, status, project, counts, user impact, last seen time, and permalink when the MCP result includes them.

**Issue deep dive:** Start with a precise issue lookup, then connect the returned project, culprit, metadata, timestamps, and status to the user's question. Separate confirmed Sentry data from likely cause.

**Status updates:** Make the smallest requested change. Prefer resolving or reopening a single verified issue ID over broad issue-list mutations.

Files in this skill

  • SKILL.md2.1 KB
  • manifest.json353 B
  • runtime-component.json287 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.