
Harbor AIops
io.github.AIops-toolsPublished by GitHub account AIops-toolsv0.2.0Updated Nov 5, 2026
Governed Harbor registry operations — 39 MCP tools with audit.
The publisher's own server: Harbor Notes
Overview
Governed Harbor container-registry operations: 39 audited MCP tools to inspect projects, artifacts, scans, GC and replication, plus guarded tag writes.
- What you can do
- Inspect component health, volume use and registry statistics
- List projects, repositories, artifacts, tags, quotas, members, labels and robot metadata
- Read vulnerability reports, scan metrics and bounded scan report logs
- Review garbage collection history, replication policies and executions, retention policies and task logs
- Diagnose by combining health, volume, GC and replication observations
- Preview and perform guarded tag creation and deletion of one proven mutable tag
- When to use it
- For teams running a Harbor container registry who want an assistant to answer questions about projects, artifacts, vulnerabilities, quotas, GC and replication, or to make narrow, audited tag changes with dry-run previews.
- Requirements
- Local Python 3.11+ environment with uv, plus a reachable Harbor instance over HTTPS. Configure targets in a config file or via the init command, store the target password in the encrypted secret store, and optionally set HARBOR_AIOPS_MASTER_PASSWORD for noninteractive access. A custom CA PEM can be supplied.
Installation
In SourceWeft
- Open Harbor AIops in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Harbor AIops
Governed Harbor container-registry operations with 39 MCP tools and corresponding CLI commands. Every call is audited and budgeted by the bundled governance harness. Artifact scan, tag creation and high-risk tag deletion have dry-run previews; uncertain results are reported as outcomeUnknown.
What it checks
- Component health and system volume use.
- Projects, repository inventory, artifacts, tags, vulnerability reports, quotas and project audit logs.
- Registry statistics, project members, tag immutability rules, labels and robot metadata (secrets redacted).
- Latest registry-wide and scheduled scan metrics, plus bounded artifact scan report logs.
- Guarded deletion of one proven, mutable tag with an absence post-check.
- Garbage collection execution history.
- GC execution details and bounded plain-text logs.
- Replication policies, executions, tasks and bounded task logs.
- Retention policy, execution, tasks and bounded task logs by actual IDs.
harbor_diagnosecombines health, volume, GC and replication observations. Failed probes appear as errors withdata: null.
Lists have items, returned, limit, and measured truncated fields. They are capped at 500 records per call.
Setup from source
Requires Python 3.11+, uv, and a Harbor instance. Install locally with uv sync --dev. Run uv run harbor-aiops init to configure an HTTPS target and encrypt its password, or create ~/.harbor-aiops/config.yaml with a targets list:
Run uv run harbor-aiops secret set primary, then uv run harbor-aiops doctor and uv run harbor-aiops diagnose. The MCP entry point is uv run harbor-aiops-mcp. Set HARBOR_AIOPS_MASTER_PASSWORD for noninteractive secret-store access. TLS verification is enabled by default; ca_file accepts a custom CA PEM.
Scope and verification
The scan-artifact command starts an asynchronous scan and reports an unknown final outcome until its status is checked. create-tag proves the tag was absent and checks that it appeared after the write. delete-tag requires an exact mutable tag on the specified digest, previews the target and confirms absence after deletion. Neither tag write mints an undo token because immutability and later artifact changes can make the inverse unsafe. Retention execution, replication restart, GC start/stop, artifact deletion and policy changes remain outside this release until their actual outcomes and recovery paths can be verified on disposable Harbor. See verification. Missing operations and live-environment feedback are welcome as issues or PRs.
Development
uv run pytest -q, uv run ruff check ., and uv run bandit -r harbor_aiops -ll are local checks. Root handbook gates must pass before release.
Source: README.md at commit 550a980
Tools
0Version history
1- v0.2.0LatestNov 5, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Harbor integrations
Harbor Notes
my.harborOfficial publisher
Search, read, write and organize your notes and tasks in Harbor, an Evernote-compatible notes app.

Harbor
Published by GitHub account oreondev
Read-only MCP server for a Harbor container registry, letting an assistant inspect projects, artifacts, vulnerabilities, robots and replication.

Harbor
Published by GitHub account 7jb28c9mtk-web
Remote Harbor MCP server that lets an assistant read your portfolio, program and project data and add tasks, risks and check-ins.

Agent Harbor pay-per-call tools
Published by GitHub account yandyman
Agent Harbor pay-per-call tools's hosted MCP server; no sign-in required; Streamable HTTP; 10 tools.

BioHarbor
Published by GitHub account danielLuo2
BioHarbor is a local MCP server that lets an AI agent run real bioinformatics compute — sequence stats, translation, ORF finding, MMseqs2 homology search and…