# io.github.akillam/helloaigent-publisher (npm · @helloaigent-dev/publisher)

Run a Hello Aigent feed from your agent: create feeds, publish signed updates, read analytics.

- Trust score: 69/100 (medium)
- Change this week: +41
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@helloaigent-dev/publisher`: 69/100 (this document), [markdown](https://verifymcp.io/servers/akillam-helloaigent-publisher/helloaigent-dev-publisher.md), [page](https://verifymcp.io/servers/akillam-helloaigent-publisher/helloaigent-dev-publisher)

## Channel facts

- Registry: `npm`
- Package: `@helloaigent-dev/publisher`
- Version: `0.1.0`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **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**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 777 tokens (~86/item across 9 items; 9 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**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 96% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add akillam-helloaigent-publisher -- npx -y @helloaigent-dev/publisher
```

### Codex

```bash
codex mcp add akillam-helloaigent-publisher -- npx -y @helloaigent-dev/publisher
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add akillam-helloaigent-publisher --command npx --arg -y --arg @helloaigent-dev/publisher
```

### Hermes

```yaml
mcp_servers:
  akillam-helloaigent-publisher:
    command: "npx"
    args: ["-y", "@helloaigent-dev/publisher"]
```

### Other

```json
{
  "mcpServers": {
    "akillam-helloaigent-publisher": {
      "command": "npx",
      "args": [
        "-y",
        "@helloaigent-dev/publisher"
      ]
    }
  }
}
```

## 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.

### 2026-08-03 (score 69, +33)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → excellent
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Stability: unverified → 0.27
- [functional] Licence: MIT

### 2026-08-01 (score 36, +8)

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

### 2026-07-27 (score 28)

First indexed and scored.

## MCP tools (9)

### `hello_aigent_create_feed` (~161 tokens)

Create a Hello Aigent feed (a stream agents subscribe to). Mints an Ed25519 signing keypair and a per-feed publisher token, and returns the generated discovery file. The publisher token is shown ONCE — save it; it authorizes publishing to this feed. Requires the admin token.

Input parameters:

- `description` (string, required): What this feed publishes
- `id` (string): Optional feed id slug; auto-derived from the title if omitted
- `publisher_name` (string, required): The publisher/brand name
- `publisher_site` (string, required): The publisher website URL
- `title` (string, required): Human title, e.g. "Acme Roast Drops"
- `topics` (array): Topics, e.g. ["restocks","offers"]

### `hello_aigent_list_feeds` (~35 tokens)

List the feeds you own (id, title, topics, latest_seq, discovery URL). Requires the admin token.

### `hello_aigent_publish` (~159 tokens)

Publish a signed update to a feed. The server Ed25519-signs the envelope; subscribed agents verify it before acting. Uses the feed's publisher token (or the admin token). IMPORTANT: publishing sends to every subscriber — confirm the content with the feed owner before calling.

Input parameters:

- `actions` (array): Callable actions (name, endpoint, input_schema)
- `body_markdown` (string, required): Markdown body of the update
- `data` (object): Structured data, e.g. { "sku": "ETH-YIRG" }
- `feed` (string, required): Feed id to publish to
- `summary` (string, required): One-line summary shown to agents
- `title` (string, required)
- `type` (string, required): Update type

### `hello_aigent_report_event` (~113 tokens)

Report an action outcome for a subscription — the "acted" signal that powers the analytics funnel. Call this after a subscriber's agent completes one of your callable actions. Uses the feed's publisher token (or the admin token).

Input parameters:

- `action_name` (string, required): The action that completed, e.g. "claim_offer"
- `feed` (string, required): Feed id
- `subscription_id` (string, required): The subscription that acted
- `update_id` (string): The update the action came from, if known

### `hello_aigent_overview` (~58 tokens)

Overview for a feed: subscribers, fetches today, 7-day return rate, signed-update count, a fetch sparkline, and recent agent-attributed activity. Requires the admin token.

Input parameters:

- `feed` (string, required): Feed id

### `hello_aigent_funnel` (~60 tokens)

The subscribed → returned → acted cohort funnel for a feed over a window, with return-rate and act-rate. Requires the admin token.

Input parameters:

- `feed` (string, required): Feed id
- `window` (string): Window (default 30d)

### `hello_aigent_event_log` (~70 tokens)

Filterable audit of feed events (subscribe/fetch/action/unsubscribe), newest first, agent-attributed. Requires the admin token.

Input parameters:

- `feed` (string, required): Feed id
- `limit` (integer): Max rows (default 50)
- `type` (string): Filter by event type

### `hello_aigent_subscribers` (~59 tokens)

The feed's subscriber list — the audience you own: agent, principal, topics, consent scope, last fetch, and status (active/dormant/revoked). Requires the admin token.

Input parameters:

- `feed` (string, required): Feed id

### `hello_aigent_discovery_file` (~62 tokens)

Get the generated discovery file (hello-aigent.json) for a feed — host it at your site's /.well-known/hello-aigent.json so agents can find and subscribe. Public; no token needed.

Input parameters:

- `feed` (string, required): Feed id

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/akillam-helloaigent-publisher/helloaigent-dev-publisher#diagnostics

## Score history

- 2026-08-03: 69
- 2026-08-02: 36
- 2026-08-01: 36
- 2026-07-31: 28
- 2026-07-30: 28
- 2026-07-28: 28
- 2026-07-27: 28

## Links

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