mcp-qa

작성자: sentry

QA MCP tool changes with local CLI and real agent clients. Use when explicitly invoked via /mcp-qa or when asked to QA MCP tool changes end-to-end.

npx skills add https://github.com/getsentry/sentry-mcp --skill mcp-qa

Verify MCP tool behavior end-to-end before committing or creating a PR. Prefer agent-callable paths over browser or inspector workflows.

1. Quality Gate

pnpm run tsc && pnpm run lint && pnpm run test

Fix any failures before proceeding.

2. Stdio CLI

This is the primary QA path for tool behavior. Stdio runs the local MCP server against prod Sentry without depending on the Cloudflare worker, local /mcp route, or Cloudflare OAuth configuration. When validating code or tool changes, build first because the test client launches packages/mcp-server/dist/index.js:

pnpm -w run build

Check auth first:

pnpm --filter @sentry/mcp-server start auth status

If no cache exists, warm the device-code cache:

pnpm --filter @sentry/mcp-server start auth login

Device-code auth uses the bundled stdio public client ID, requires no client secret, is separate from the Cloudflare OAuth app, and caches the token in ~/.sentry/mcp.json.

First prove startup and auth:

pnpm -w run cli --transport stdio --list-tools
pnpm -w run cli --transport stdio "who am I?"

Then prove the changed behavior with a realistic prod prompt. Choose a prompt that requires the new or modified tool path, uses real org/project/resource inputs, and asks for enough detail to prove the endpoint response is usable.

pnpm -w run cli --transport stdio \
  "<prompt that exercises the changed MCP behavior against prod data>"

Passing QA means the local CLI prints Connected to MCP server (stdio), uses the expected MCP tool path, and returns real prod data that demonstrates the behavior. For catalog tools, expect search_sentry_tools followed by execute_sentry_tool(name: <changed_tool>). For direct tools, expect the tool name in the transcript. --list-tools alone is not QA.

For mutating catalog-only tools, avoid live prod changes unless there is a disposable resource prepared for the test. Add or run a server-level execute_sentry_tool dispatch test with MSW coverage to prove catalog discovery, generated schema exposure, constraint injection, and tool dispatch without changing real Sentry data.

For output-format changes, also inspect the raw MCP tool result when possible, not only the LLM's final answer. The final answer can add model-specific text that is not part of the tool response. Review raw tool output against docs/contributing/tool-responses.md: it should be user-facing, structured, and free of raw API JSON, internal implementation IDs, empty placeholders, and unrelated instructions.

3. Real Agent Clients

Use these when validating Claude Code, Codex, or behavior that only reproduces in a real agent client:

pnpm -w run build

What this verifies:

  • The CLI is installed and can see the named MCP server
  • The provider can run a connectivity prompt against Sentry MCP
  • The final answer includes the authenticated email from whoami

For agent-client-specific behavior, replace the default harness prompt with the same realistic prod prompt used for stdio QA. Passing QA requires the same changed-tool transcript evidence, not only whoami.

as an isolated auth cache. Real clients do not give stdio subprocesses a TTY, so warm the cache before running the harness. It also runs the built packages/mcp-server/dist/index.js, so build first to avoid stale code.

4. Cloudflare HTTP Only When Relevant

Run this only when changes touch Cloudflare, HTTP transport, /mcp routing, OAuth, web UI, or hosted-server compatibility. It is not required for ordinary tool handler changes.

Start the dev server in a separate terminal or background process:

pnpm dev

Then verify it is reachable:

curl -s -o /dev/null -w "%{http_code}" http://localhost:5173/

If pnpm dev fails because local Cloudflare/Wrangler is not configured, note the failure and continue with stdio QA for tool behavior.

pnpm -w run cli "who am I?"
pnpm -w run cli "list all available tools"
pnpm -w run cli "<same realistic prod prompt used for stdio QA>"
pnpm -w run cli --mcp-host=http://localhost:5173/mcp/<org> \
  "<same realistic prod prompt used for stdio QA>"
pnpm -w run cli --mcp-host=http://localhost:5173/mcp/<org>/<project> \
  "<same realistic prod prompt used for stdio QA>"

Look for Connected to MCP server (<resolved MCP URL>) to confirm HTTP transport, plus the same changed-tool transcript evidence required for stdio QA. Use scoped /mcp/<org> or /mcp/<org>/<project> URLs when validating routing, OAuth, or resource-scope behavior. Use --setup repo --server sentry to test the hosted server instead.

5. Source Build Stdio Only When Relevant

Use this when specifically checking the built local stdio server rather than dev-time source execution:

pnpm -w run build
pnpm --filter @sentry/mcp-server start auth status
pnpm -w run cli --transport stdio "who am I?"

Look for Connected to MCP server (stdio) to confirm stdio transport.

sentry의 다른 스킬

generate-frontend-forms
sentry
Sentry의 새로운 폼 시스템을 사용하여 폼을 생성하는 가이드입니다. 폼, 폼 필드, 유효성 검사 또는 자동 저장 기능을 구현할 때 사용하세요.
official
sentry-snapshots-cocoa
sentry
Apple/Cocoa 프로젝트를 위한 전체 Sentry Snapshots 설정입니다. "SnapshotPreviews 설정", "Apple 스냅샷 테스트 설정", "Apple 스냅샷 업로드" 요청 시 사용하세요.
official
architecture-review
sentry
직원 수준의 코드베이스 건강 검토. 모놀리식 모듈, 무음 실패, 타입 안전성 격차, 테스트 커버리지 구멍, LLM 친화성 문제를 찾습니다.
official
linear-type-labeler
sentry
Linear 이슈를 분류하고, 각 이슈의 제목과 설명 내용을 기반으로 Sentry 워크스페이스의 레이블 분류 체계에서 Type 레이블을 적용합니다.
official
vercel-react-best-practices
sentry
Vercel Engineering의 React 및 Next.js 성능 최적화 가이드라인입니다. 이 스킬은 React/Next.js 코드를 작성, 검토 또는 리팩토링할 때 사용해야 합니다.
official
bump-size-limit
sentry
.size-limit.js 파일에서 크기 제한을 올립니다. size-limit CI 검사가 실패할 때 사용합니다. 사용자가 크기 제한 실패, 번들 크기 검사 실패, CI 크기 문제를 언급할 때 사용하세요.
official
generate-migration
sentry
Sentry용 Django 데이터베이스 마이그레이션을 생성합니다. 마이그레이션 생성, 컬럼이나 테이블 추가/제거, 인덱스 추가, 또는 마이그레이션 충돌 해결 시 사용하세요.
official
security-review
sentry
코드 변경 사항에서 악용 가능한 애플리케이션 보안 취약점을 찾습니다. Warden 보안 스캔, 앱 보안 검토, OWASP 스타일 점검, 인증 또는…에 사용합니다.
official