# io.github.bzdOS/hubd (npm · @bzdos/hubd)

The project tracker for teams of humans and AI agents — in plain files. MCP server + CLI.

- Trust score: 70/100 (medium)
- Change this week: −10
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- npm · `@bzdos/hubd`: 70/100 (this document), [markdown](https://verifymcp.io/servers/bzdos-hubd/bzdos-hubd.md), [page](https://verifymcp.io/servers/bzdos-hubd/bzdos-hubd)

## Channel facts

- Registry: `npm`
- Package: `@bzdos/hubd`
- Version: `0.4.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-04.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 8 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1409 tokens (~82/item across 17 items; 17 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 85/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 56% of tool parameters carry a description.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add bzdos-hubd -- npx -y @bzdos/hubd
```

### Codex

```bash
codex mcp add bzdos-hubd -- npx -y @bzdos/hubd
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "bzdos-hubd": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@bzdos/hubd"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add bzdos-hubd --command npx --arg -y --arg @bzdos/hubd
```

### Hermes

```yaml
mcp_servers:
  bzdos-hubd:
    command: "npx"
    args: ["-y", "@bzdos/hubd"]
```

### Other

```json
{
  "mcpServers": {
    "bzdos-hubd": {
      "command": "npx",
      "args": [
        "-y",
        "@bzdos/hubd"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-04 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-03 (score 69, +3)

- [functional improvement] Stability: unverified → 0.23

### 2026-08-01 (score 66, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-07-31 (score 51, −11)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 62, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 80, +33)

- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 56
- [functional] First check of Schema quality: good

### 2026-07-26 (score 47)

First indexed and scored.

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

## MCP tools (17)

### `hub_sync` (~110 tokens)

Sync a project folder into the hub. Collects git facts automatically; pass digest (your own summary of state/next steps) and the card is rewritten.

Input parameters:

- `agent` (string): Who is syncing (e.g. claude-cowork, cursor, executor)
- `digest` (string): Agent-written summary: status, recent work, next steps, blockers
- `name` (string): Project name (default: folder name)
- `path` (string, required): Absolute path to the project folder

### `hub_card_set` (~104 tokens)

Create or update a project card from just a name and a digest — no folder needed (unlike hub_sync). Use it to capture a project that is not a local git checkout, e.g. when harvesting a dialog. Preserves any hand-written frontmatter and Facts.

Input parameters:

- `by` (string): who is writing
- `digest` (string, required): the card digest: 3-6 lines of current state
- `project` (string, required): project name or slug

### `hub_report` (~56 tokens)

Append a session report to the shared journal: what was done / broken / blocked.

Input parameters:

- `agent` (string, required)
- `kind` (string): default: note
- `project` (string, required)
- `text` (string, required)

### `hub_status` (~75 tokens)

Snapshot of every project at once: the latest digest of each, when it was last synced, and its open-task count, plus the most recent shared-journal entries. Best for orienting at the start of a session. For a deadline-sorted to-do list use hub_brief; for one project in depth use hub_get.

### `hub_get` (~58 tokens)

Everything about ONE project: its full card (digest + facts), recent journal entries for it, and any active soft-locks. Use after hub_status or hub_search points you at a project.

Input parameters:

- `project` (string, required): project slug or name

### `hub_search` (~56 tokens)

Full-text search across every project card and the entire journal, archived months included. Returns each matching line with its location. Use to find where something was discussed or decided.

Input parameters:

- `query` (string, required): plain-text substring, case-insensitive

### `hub_task_add` (~132 tokens)

Add a task to the shared cross-project backlog.

Input parameters:

- `assignee` (string): agent name or owner, optional
- `by` (string): who adds
- `cat` (string): task category, optional
- `deadline` (string): YYYY-MM-DD, optional
- `depends_on` (array): task ids this task waits on
- `importance` (string): default normal
- `project` (string, required)
- `resources` (array): resource slugs this task touches (host/vm/service/...) — a structured link task → resource, not prose
- `text` (string, required)

### `hub_task_list` (~34 tokens)

List backlog tasks. Filter by project and/or status.

Input parameters:

- `project` (string)
- `status` (string)

### `hub_task_update` (~108 tokens)

Update a task: close it (status=done), reassign, edit text/deadline/cat.

Input parameters:

- `assignee` (string)
- `by` (string)
- `cat` (string)
- `deadline` (string)
- `depends_on` (array): task ids this task waits on
- `id` (integer, required)
- `resources` (array): resource slugs this task touches
- `status` (string)
- `text` (string)

### `hub_brief` (~64 tokens)

Morning brief across all projects: open tasks (deadlines first), journal since N hours, stale cards, active claims.

Input parameters:

- `hours` (integer): journal window, default 48
- `staleDays` (integer): card considered stale after N days, default 7

### `hub_kanban` (~59 tokens)

The board as data: open tasks split into queued (unassigned) and in-progress (assigned), plus done-in-the-last-day and recent journal — the same view the read-only web kanban renders. Each task carries blocked and overdue flags.

### `hub_claim` (~72 tokens)

Soft-lock a work area so other agents see it (e.g. area="public/index.html"). Not enforced — informational.

Input parameters:

- `agent` (string, required)
- `area` (string, required)
- `note` (string)
- `project` (string, required)
- `ttlMin` (integer): default 240

### `hub_release` (~51 tokens)

Release a soft-lock. Pass id, or project+area+agent.

Input parameters:

- `agent` (string)
- `area` (string)
- `id` (string)
- `project` (string)

### `hub_resource_set` (~219 tokens)

Create or update a resource — an infrastructure/topology entity: host, vm, service, endpoint, or provider. Structured attributes (type, address, os, provider, status) and typed relationships go in fields, NOT prose. Use this instead of describing infra inside a card digest.

Input parameters:

- `address` (string): ip / hostname / url, optional
- `by` (string): who is writing
- `digest` (string): one-line description (keep prose minimal)
- `edges` (object): typed relationships, merged with existing: {"runs_on":["hubd"],"depends_on":["postgres"]}. Values are target slugs.
- `os` (string)
- `provider` (string): libvirt | cloudflare | bare-metal | ...
- `slug` (string, required): resource id, e.g. "myvm" or "board.hubd.net"
- `status` (string): live | down | planned | retired
- `type` (string): host | vm | service | endpoint | provider | ... (open vocabulary)

### `hub_resource_list` (~37 tokens)

List resource cards (hosts, vms, services, endpoints, providers). Optionally filter by type.

Input parameters:

- `type` (string)

### `hub_resource_get` (~27 tokens)

One resource card plus its inbound and outbound typed relationships.

Input parameters:

- `slug` (string, required)

### `hub_graph` (~105 tokens)

The typed relationship graph across projects AND resources: who runs where, what depends on / deploys to / exposes what. Edges are frontmatter [[links]] keyed by relation (runs_on, depends_on, deploys_to, exposes, part_of, ...). Returns nodes, edges, and dangling links. Filter by project or type.

Input parameters:

- `project` (string): only edges touching this project/resource slug
- `type` (string): only edges touching a node of this type

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/bzdos-hubd/bzdos-hubd#diagnostics

## Score history

- 2026-08-04: 70
- 2026-08-03: 69
- 2026-08-02: 66
- 2026-08-01: 66
- 2026-07-31: 51
- 2026-07-30: 62
- 2026-07-28: 80
- 2026-07-27: 80
- 2026-07-26: 47

## Links

- npm package: https://www.npmjs.com/package/@bzdos/hubd
- Socket report: https://socket.dev/npm/package/@bzdos/hubd
- Repository: https://github.com/bzdOS/hubd
- Changelog RSS feed: https://verifymcp.io/servers/bzdos-hubd/bzdos-hubd/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/bzdos-hubd/bzdos-hubd/changelog.json
- HTML version of this page: https://verifymcp.io/servers/bzdos-hubd/bzdos-hubd