Harbor AIops
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HARBOR_AIOPS_MASTER_PASSWORD | Yes | Master password for noninteractive access to the encrypted Harbor secret store. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Governed Harbor registry operations: health, volume, GC, replication and retention diagnosis. Every tool is audited and budgeted.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| harbor_statisticsB | [READ] Get registry-wide project and repository counts. |
| harbor_project_membersC | [READ] List a Harbor project's members with measured truncation. |
| harbor_immutable_rulesC | [READ] List tag immutability rules for a project. |
| harbor_robot_accountsB | [READ] List robot account metadata with any returned secret redacted. |
| harbor_labelsC | [READ] List Harbor labels with measured truncation. |
| harbor_scan_all_metricsC | [READ] Get metrics from the latest registry-wide scan. |
| harbor_scheduled_scan_metricsB | [READ] Get metrics from the latest scheduled registry-wide scan. |
| harbor_scan_logB | [READ] Read a bounded artifact scan report log by report ID. |
| harbor_gc_executionB | [READ] Get one Harbor garbage-collection execution's current state. |
| harbor_gc_logC | [READ] Read the bounded plain-text log of a GC execution. |
| harbor_replication_task_logB | [READ] Read the bounded plain-text log of a replication task. |
| harbor_retention_task_logC | [READ] Read the bounded plain-text log of a retention task. |
| harbor_projectsB | [READ] List visible Harbor projects with measured truncation. |
| harbor_projectC | [READ] Get one Harbor project by name or ID. |
| harbor_project_summaryC | [READ] Get Harbor's repository, artifact and storage summary for a project. |
| harbor_repositoriesC | [READ] List repositories inside a Harbor project. |
| harbor_artifactsC | [READ] List artifacts, tags and scan overviews in a repository. |
| harbor_artifactC | [READ] Get one artifact with tags, scan overview and immutability status. |
| harbor_tagsB | [READ] List tags and their immutable status for an artifact. |
| harbor_vulnerabilitiesB | [READ] Get Harbor's stored vulnerability report for an artifact. |
| harbor_replication_policiesC | [READ] List replication policies with measured truncation. |
| harbor_replication_policyC | [READ] Get a replication policy by its Harbor ID. |
| harbor_replication_executionC | [READ] Get the current state of one replication execution. |
| harbor_retention_tasksB | [READ] List tasks of a retention execution, including per-task failures. |
| harbor_quotasC | [READ] List registry quota usage and limits. |
| harbor_project_audit_logsB | [READ] List a project's Harbor audit logs; not the MCP governance audit. |
| harbor_healthA | [READ] Get Harbor component health; unknown components remain visible. |
| harbor_volumesC | [READ] Get Harbor storage volume usage from the system-info endpoint. |
| harbor_gc_historyC | [READ] List garbage-collection executions with measured truncation. |
| harbor_replication_executionsC | [READ] List replication executions, optionally filtered by upstream status. |
| harbor_replication_tasksC | [READ] List tasks for one replication execution. |
| harbor_retention_policyC | [READ] Get one retention policy by its actual Harbor policy id. |
| harbor_retention_executionsC | [READ] List executions of one retention policy with measured truncation. |
| harbor_diagnoseC | [READ] Correlate health, volume, GC and replication probes; show partial failures. |
| undo_listA | [READ] List recorded, not-yet-applied undo tokens (most recent first). Each entry names the original tool, the inverse tool that One extra row is read so Each entry carries Args: limit: Max rows to return (default 50, capped at 500). target: Unused (undo state is host-local); accepted for CLI uniformity. |
| undo_applyA | [WRITE][risk=medium] Apply a recorded undo by dispatching its inverse tool. The inverse runs through its own governed tool, so it is audited under its own risk tier. Pass dry_run=True to preview the inverse call without executing it. A token can only be applied once. Args:
undo_id: The undoId from undo_list (or an |
| harbor_scan_artifactC | [WRITE] Start an artifact scan; accepted does not mean scan completed. |
| harbor_create_tagB | [WRITE] Create a tag only if its absence was proven and verify it appeared. |
| harbor_delete_tagC | [WRITE] Delete one verified, mutable tag; no safe undo is minted. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 39 tools
Tools target distinct Harbor resources, but the singular/plural pairs (harbor_project vs harbor_projects, harbor_replication_policy vs harbor_replication_policies, harbor_replication_execution vs harbor_replication_executions, harbor_retention_executions vs harbor_retention_tasks) plus the log/metric variants create easy misselection traps. Descriptions do carry the distinguishing detail, but an agent must read them carefully rather than pattern-match on the name.
Nearly all tools use a consistent harbor_<noun> snake_case convention with singular for get-one and plural for list, which is readable and predictable. The deviations are undo_list/undo_apply (outside the harbor_ namespace and verb-first) and harbor_diagnose, which are minor but noticeable.
39 tools is heavy for a single server and pushes well past the comfortable 3-15 range; several near-duplicates (harbor_scan_all_metrics vs harbor_scheduled_scan_metrics, three separate replication/retention log tools, harbor_diagnose overlapping the probes it correlates) inflate the surface. Each maps to a real Harbor endpoint, but the set is broad enough to burden tool selection.
Read/diagnostic coverage of the registry is strong — projects, repos, artifacts, tags, scans, quotas, GC, replication, retention, health and audit logs are all reachable. Write coverage is thin: only scan_artifact, create_tag and delete_tag mutate state, so project/repository/artifact/policy lifecycle operations and credential or quota management are notable gaps.