harbor-registry-mcp
harbor-registry-mcp
Servidor MCP para Harbor Registry. Permite que un agente LLM (Claude Code, Cursor, OpenCode, etc.) liste proyectos, repositorios y artefactos, ejecute informes de almacenamiento, encuentre candidatos a limpieza y elimine artefactos sin etiquetas o antiguos, todo con medidas de seguridad (ejecución en seco por defecto para eliminaciones masivas).
Python, FastMCP, transporte stdio.
Funciona con cualquier instancia de Harbor 2.x, ya sea SaaS o autohospedada / on-premise.
¿Por qué otro MCP de Harbor?
Existen un par de MCPs de Harbor en la comunidad (nomagicln/mcp-harbor, bupd/harbor-mcp-server), pero solo exponen los endpoints básicos de listar/obtener. Este añade informes de almacenamiento, candidatos a limpieza, eliminación de artefactos sin etiquetas y eliminación de artefactos antiguos con ejecución en seco, las operaciones que los ingenieros de DevOps realmente necesitan para recuperar espacio en disco.
Related MCP server: Harbor MCP Server
Aspectos destacados del diseño
Anotaciones de herramientas: las herramientas de solo lectura tienen
readOnlyHint: True; las destructivas (harbor_delete_*) llevandestructiveHint: Truepara que los clientes MCP soliciten confirmación.Ejecución en seco por defecto en limpiezas masivas (
harbor_delete_old_artifacts(dry_run=True)): el agente debe cambiarlo para ejecutar.Salida estructurada: cada herramienta devuelve una carga útil tipada (TypedDict) + un resumen en markdown.
Errores estructurados: 401 / 403 / 404 / 429 / 5xx mapeados a sugerencias accionables.
Validación de entrada Pydantic para cada argumento.
Instantánea de vulnerabilidades:
harbor_list_artifactsmuestra el estado del escaneo y los recuentos siwith_scan_overviewestá habilitado.
Características (8 herramientas)
Descubrimiento e inspección
harbor_list_projects: proyectos con recuentos de repositorios y visibilidadharbor_list_repos: repositorios en un proyectoharbor_list_artifacts: artefactos en un repositorio con etiquetas/tamaño/estado de escaneoharbor_storage_report: desglose completo del almacenamiento del proyecto (todos los repos × todos los artefactos)
Planificación de limpieza
harbor_cleanup_candidates: sugiere qué eliminar (sin etiquetas, nunca extraídos, versiones antiguas)
Ejecución de limpieza (destructiva)
harbor_delete_artifact: elimina un solo artefacto por etiqueta o resumen (digest)harbor_delete_untagged: elimina todos los artefactos sin etiquetas en un proyecto/repositorioharbor_delete_old_artifacts: mantiene los N más recientes por repositorio, elimina el resto (ejecución en seco por defecto)
Instalación
Requiere Python 3.10+.
# via uvx (recommended)
uvx --from harbor-registry-mcp harbor-registry-mcp
# or via pipx
pipx install harbor-registry-mcpConfiguración
claude mcp add harbor -s project \
--env HARBOR_URL=https://harbor.example.com \
--env HARBOR_USERNAME='robot$your-robot' \
--env HARBOR_PASSWORD=your-robot-token \
--env HARBOR_SSL_VERIFY=true \
-- uvx --from harbor-registry-mcp harbor-registry-mcpO en .mcp.json:
{
"mcpServers": {
"harbor": {
"type": "stdio",
"command": "uvx",
"args": ["--from", "harbor-registry-mcp", "harbor-registry-mcp"],
"env": {
"HARBOR_URL": "https://harbor.example.com",
"HARBOR_USERNAME": "robot$your-robot",
"HARBOR_PASSWORD": "${HARBOR_PASSWORD}",
"HARBOR_SSL_VERIFY": "true"
}
}
}
}Comprobar:
claude mcp list
# harbor: uvx --from harbor-registry-mcp harbor-registry-mcp - ✓ ConnectedVariables de entorno
Variable | Requerido | Descripción |
| sí | URL de Harbor (sin barra diagonal al final) |
| sí | Nombre de usuario de Harbor: se recomienda cuenta de robot |
| sí | Contraseña o token de robot |
| no |
|
Ejemplo de uso
"Informe de almacenamiento para el proyecto
einvy-pub""Encontrar candidatos a limpieza en
qa-assistant: mantener los 3 más recientes""Eliminar todos los artefactos sin etiquetas en
qa-assistant""Ejecución en seco de eliminación de artefactos antiguos en
qa-assistant/pgvector-rag, mantener 1 más reciente""¿Qué hay en
einvy-pub/my-image?"
Seguridad
Las herramientas de lectura usan
readOnlyHint: True: no se necesita confirmación.Las herramientas de eliminación usan
destructiveHint: True: los clientes deben confirmar.harbor_delete_old_artifactstienedry_run=Truepor defecto; el agente debe establecer explícitamentedry_run=Falsepara eliminar realmente.harbor_cleanup_candidateses de solo lectura: solo sugiere candidatos, nunca elimina.
Desarrollo
git clone https://github.com/mshegolev/harbor-registry-mcp.git
cd harbor-registry-mcp
pip install -e '.[dev]'
pytestLicencia
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