harbor-registry-mcp
harbor-registry-mcp
Harbor Registry를 위한 MCP 서버입니다. LLM 에이전트(Claude Code, Cursor, OpenCode 등)가 프로젝트, 리포지토리, 아티팩트를 나열하고, 스토리지 보고서를 실행하며, 정리 대상 후보를 찾고, 태그가 없거나 오래된 아티팩트를 삭제할 수 있게 합니다. 모든 작업에는 안전 장치가 포함되어 있습니다(대량 삭제 시 기본적으로 드라이런(dry-run) 실행).
Python, FastMCP, stdio 전송을 사용합니다.
SaaS 또는 자체 호스팅/온프레미스 등 모든 Harbor 2.x 인스턴스에서 작동합니다.
왜 다른 Harbor MCP인가요?
기존에 커뮤니티 Harbor MCP(nomagicln/mcp-harbor, bupd/harbor-mcp-server)가 존재하지만, 이들은 기본적인 목록 조회/가져오기 엔드포인트만 제공합니다. 이 서버는 스토리지 보고서, 정리 대상 후보 찾기, 태그 없는 아티팩트 삭제, 드라이런을 포함한 오래된 아티팩트 삭제 기능을 추가하여 DevOps 엔지니어가 디스크 공간을 확보하는 데 실제로 필요한 작업을 수행할 수 있게 합니다.
Related MCP server: Harbor MCP Server
설계 특징
도구 주석 — 읽기 전용 도구는
readOnlyHint: True를 가지며, 파괴적인 도구(harbor_delete_*)는destructiveHint: True를 포함하여 MCP 클라이언트가 확인을 요청하도록 합니다.기본 드라이런 — 대량 정리 작업(
harbor_delete_old_artifacts(dry_run=True))은 기본적으로 드라이런으로 실행되며, 에이전트가 이를 명시적으로 변경해야 실행됩니다.구조화된 출력 — 모든 도구는 타입이 지정된 페이로드(TypedDict)와 마크다운 요약을 반환합니다.
구조화된 오류 — 401 / 403 / 404 / 429 / 5xx 오류가 실행 가능한 힌트로 매핑됩니다.
Pydantic 입력 검증 — 모든 인자에 대해 검증을 수행합니다.
취약점 스냅샷 —
with_scan_overview가 활성화된 경우harbor_list_artifacts가 스캔 상태와 개수를 표시합니다.
기능 (8개 도구)
탐색 및 검사
harbor_list_projects— 리포지토리 개수 및 공개 여부를 포함한 프로젝트 목록harbor_list_repos— 프로젝트 내 리포지토리 목록harbor_list_artifacts— 태그/크기/스캔 상태를 포함한 리포지토리 내 아티팩트 목록harbor_storage_report— 전체 프로젝트 스토리지 분석 (모든 리포지토리 × 모든 아티팩트)
정리 계획
harbor_cleanup_candidates— 삭제 대상 제안 (태그 없음, 한 번도 풀(pull)되지 않음, 오래된 버전)
정리 실행 (파괴적)
harbor_delete_artifact— 태그 또는 다이제스트별로 단일 아티팩트 삭제harbor_delete_untagged— 프로젝트/리포지토리 내 태그 없는 모든 아티팩트 삭제harbor_delete_old_artifacts— 리포지토리당 최신 N개를 유지하고 나머지는 삭제 (기본값: 드라이런)
설치
Python 3.10 이상이 필요합니다.
# via uvx (recommended)
uvx --from harbor-registry-mcp harbor-registry-mcp
# or via pipx
pipx install harbor-registry-mcp설정
claude mcp add harbor -s project \
--env HARBOR_URL=https://harbor.example.com \
--env HARBOR_USERNAME='robot$your-robot' \
--env HARBOR_PASSWORD=your-robot-token \
--env HARBOR_SSL_VERIFY=true \
-- uvx --from harbor-registry-mcp harbor-registry-mcp또는 .mcp.json 파일:
{
"mcpServers": {
"harbor": {
"type": "stdio",
"command": "uvx",
"args": ["--from", "harbor-registry-mcp", "harbor-registry-mcp"],
"env": {
"HARBOR_URL": "https://harbor.example.com",
"HARBOR_USERNAME": "robot$your-robot",
"HARBOR_PASSWORD": "${HARBOR_PASSWORD}",
"HARBOR_SSL_VERIFY": "true"
}
}
}
}확인:
claude mcp list
# harbor: uvx --from harbor-registry-mcp harbor-registry-mcp - ✓ Connected환경 변수
변수 | 필수 | 설명 |
| 예 | Harbor URL (끝에 슬래시 제외) |
| 예 | Harbor 사용자 이름 — 로봇 계정 권장 |
| 예 | 비밀번호 또는 로봇 토큰 |
| 아니오 |
|
사용 예시
"
einvy-pub프로젝트에 대한 스토리지 보고서""
qa-assistant에서 정리 대상 후보 찾기 — 최신 3개 유지""
qa-assistant에서 태그 없는 모든 아티팩트 삭제""
qa-assistant/pgvector-rag에서 오래된 아티팩트 드라이런 삭제, 최신 1개 유지""
einvy-pub/my-image에는 무엇이 있나요?"
안전성
읽기 도구는
readOnlyHint: True를 사용하여 확인이 필요 없습니다.삭제 도구는
destructiveHint: True를 사용하여 클라이언트가 확인해야 합니다.harbor_delete_old_artifacts는 기본적으로dry_run=True로 설정되어 있으며, 에이전트가 실제로 삭제하려면dry_run=False로 명시적으로 설정해야 합니다.harbor_cleanup_candidates는 읽기 전용이며, 삭제하지 않고 후보만 제안합니다.
개발
git clone https://github.com/mshegolev/harbor-registry-mcp.git
cd harbor-registry-mcp
pip install -e '.[dev]'
pytest라이선스
MIT © Mikhail Shchegolev
Available Tools
8 toolsharbor_cleanup_candidatesARead-onlyIdempotent
Suggest which artifacts could be deleted to reclaim space.
READ-ONLY — never deletes anything; just produces a list with
reasons. Use harbor_delete_artifact / harbor_delete_untagged /
harbor_delete_old_artifacts to act on the results.
Reasons emitted:
- untagged — artifact has no tags (orphaned layer)
- never_pulled — artifact has never been pulled (and is past
the keep_latest_per_repo cutoff)
- old_version — artifact is older than the keep_latest_per_repo
newest tagged artifacts
Inputs: project_name (required), include_untagged, include_zero_pulls, keep_latest_per_repo. Returns: project, candidates_count, total_reclaimable, total_reclaimable_bytes, +2 more
harbor_delete_artifactADestructive
Delete a single artifact by tag or digest.
DESTRUCTIVE & IRREVERSIBLE — Harbor immediately removes the manifest from its catalogue; the underlying blobs are reclaimed by the next GC sweep. There is no soft-delete or undo.
Returns the freed space and tag list for confirmation.
Inputs: project_name (required), repository_name (required), reference (required). Returns: success, project, repository, reference, +4 more
harbor_delete_old_artifactsADestructive
Keep the N newest artifacts in a repository, delete the rest.
DESTRUCTIVE. dry_run=True is the default — the agent must
explicitly set dry_run=False to actually delete. Each entry in
to_delete carries a deleted field (True/False after
real run, None in dry-run).
Inputs: project_name (required), repository_name (required), keep_count, dry_run. Returns: project, repository, dry_run, keeping, +6 more
harbor_delete_untaggedADestructiveIdempotent
Delete all untagged artifacts in a project (or single repository).
DESTRUCTIVE. Untagged artifacts are typically orphaned layers left
behind after pushing a new tag of the same image — generally safe to
delete. The full project sweep is opaque, so the response includes
repos_scanned for visibility.
Inputs: project_name (required), repository_name. Returns: project, repos_scanned, deleted_count, freed_size, +3 more
harbor_list_artifactsARead-onlyIdempotent
List artifacts (tags) in a repository, newest first.
Each artifact carries digest, size, push/pull timestamps, scan status and vulnerability counts (if scanned).
Pagination: if has_more is True, call again with page + 1.
For repositories with hundreds of artifacts prefer harbor_storage_report
or harbor_cleanup_candidates which paginate internally.
Inputs: project_name (required), repository_name (required), page, page_size. Returns: project, repository, total_size, total_size_bytes, +6 more
harbor_list_projectsARead-onlyIdempotent
List Harbor projects, sorted by repository count (descending within the page).
Use this first to discover which Harbor projects exist before drilling in
with harbor_list_repos / harbor_list_artifacts.
Pagination: if has_more is True, call again with page + 1.
Note that sorting is per-page — agents that need a global ranking should
aggregate across pages.
Returns:
dict with keys projects_count / page / page_size /
has_more / next_page / projects (list).
Inputs: page, page_size. Returns: projects_count, page, page_size, has_more, +2 more
harbor_list_reposARead-onlyIdempotent
List repositories in a Harbor project.
Each repository is reported with artifact count and total pull count (useful for spotting unused repos before cleanup).
Pagination: if has_more is True, call again with page + 1.
Inputs: project_name (required), page, page_size. Returns: project, repositories_count, page, page_size, +3 more
harbor_storage_reportARead-onlyIdempotent
Full storage breakdown for a Harbor project.
Iterates every repository × every artifact and returns a sorted-by-size report — the canonical view for "what's eating up our quota?". Performs O(repos × artifacts) API calls; emits progress events through MCP Context.
Inputs: project_name (required). Returns: project, total_repositories, total_size, total_size_bytes, +1 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool targets a distinct operation: listing, reporting, or deleting. The cleanup candidate tool is clearly separate from the delete tools, and deletion tools are differentiated by scope (single, old, untagged). No overlapping purposes.
Most tools follow the harbor_verb_noun pattern (e.g., harbor_delete_artifact, harbor_list_projects), but harbor_storage_report uses a noun_noun pattern, breaking consistency. The prefix and general style are otherwise uniform.
Eight tools cover the essential operations for a Harbor registry: discovery (list projects, repos, artifacts), cleanup (candidates, delete single, delete old, delete untagged), and reporting (storage report). The count is well-scoped without being excessive.
The tool set provides comprehensive coverage for registry management: full lifecycle for artifacts (list, delete individual/bulk/untagged), project and repository exploration, storage analysis, and a cleanup candidate suggestion tool. No major gaps in functionality for the intended domain.
Maintenance
Related MCP Connectors
Unofficial Docker Hub MCP — wraps the Docker Hub v2 API (free, no auth required for public data)
Go MCP server for GitLab: 2 dynamic tools reach 1000+ REST/GraphQL actions. Free/CE, no paid tier.
Toggl 2.0 MCP server for tasks, projects, time entries, and workspace operations.
MCP server for LingoHub — localization projects, resources, exports and repository pushes.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceA Node.js application that provides a Model Context Protocol server for interacting with Harbor container registry, supporting operations for projects, repositories, tags, and Helm charts.21 npm7MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI models to interact with Harbor container registries to manage projects, repositories, and system configurations in real time. It provides a suite of tools for monitoring health, retrieving statistics, and performing searches across registry data.6MIT
- AlicenseNot gradedqualityDmaintenanceMCP Harbor is a Node.js application that provides a Model Context Protocol (MCP) server for interacting with Harbor container registry.MIT
- AlicenseNot gradedqualityCmaintenanceEnables interacting with a Harbor container registry through the Model Context Protocol, supporting operations for projects, repositories, tags, and Helm charts.1MIT