# H/M Article 50 Transparency Builder (remote · agents.hogarmas.net)

Free Article 50 website scanner, notice builder, and checksum verifier. No key or payment.

- Trust score: 67/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `agents.hogarmas.net`: 67/100 (this document), [markdown](https://verifymcp.io/servers/net-hogarmas-ai-transparency/mcp-ai-transparency.md), [page](https://verifymcp.io/servers/net-hogarmas-ai-transparency/mcp-ai-transparency)

## Channel facts

- Endpoint: `https://agents.hogarmas.net/mcp/ai-transparency`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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.

- **Endpoint Security**: 77/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 67/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 509 tokens (~63/item across 8 items; 4 tools + 4 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 12% 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 --transport http net-hogarmas-ai-transparency https://agents.hogarmas.net/mcp/ai-transparency
```

### Codex

```toml
[mcp_servers.net-hogarmas-ai-transparency]
url = "https://agents.hogarmas.net/mcp/ai-transparency"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "net-hogarmas-ai-transparency": {
      "type": "remote",
      "url": "https://agents.hogarmas.net/mcp/ai-transparency",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add net-hogarmas-ai-transparency --url https://agents.hogarmas.net/mcp/ai-transparency --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  net-hogarmas-ai-transparency:
    url: "https://agents.hogarmas.net/mcp/ai-transparency"
```

### Other

```json
{
  "mcpServers": {
    "net-hogarmas-ai-transparency": {
      "type": "http",
      "url": "https://agents.hogarmas.net/mcp/ai-transparency"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-08-02 (score 67, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-08-01 (score 66)

First indexed and scored.

## MCP tools (4)

### `get_ai_transparency_capabilities` (~36 tokens)

Read Article 50 notice-builder boundaries

Returns the free tools, accepted bounded facts, privacy behavior, source ruleset and truth boundaries before a scenario is submitted.

### `scan_ai_transparency_surface` (~73 tokens)

Scan observable Article 50 evidence on a public website

Reads bounded static homepage signals from one public HTTP or HTTPS website. Returns observed, not-observed and manual-review evidence without source text, a compliance score or legal certification. Private and local networks are blocked.

Input parameters:

- `url` (string, required): Public HTTP or HTTPS website to scan, for example https://example.com

### `build_ai_transparency_notice` (~268 tokens)

Build an EU AI Act Article 50 notice

Maps bounded deployment facts to a review-oriented Article 50 assessment and returns deployable HTML plus a privacy-minimized checksummed manifest. Omitted facts are treated as unsure. No names, model identifiers or free text are accepted.

Input parameters:

- `accessibleDisclosureTested` (string)
- `contentTypes` (array)
- `deepfake` (string)
- `detectionTested` (string)
- `directInteraction` (string)
- `editorialResponsibility` (string)
- `emotionOrBiometric` (string)
- `euExposure` (string)
- `humanExposure` (string)
- `humanOversightLevel` (string)
- `interactionObvious` (string)
- `locale` (string): Output language. Defaults to English.
- `machineReadableMarkImplemented` (string)
- `marketEntryDateDocumented` (string)
- `placedOnMarketBefore20260802` (string)
- `professionalUse` (string)
- `publicInterestText` (string)
- `recordsMaintained` (string)
- `role` (string)
- `standardEditingOnly` (string)
- `substantiveHumanReview` (string)
- `syntheticContent` (string)
- `visibleDisclosureImplemented` (string)

### `verify_ai_transparency_manifest` (~54 tokens)

Verify an H/M AI transparency manifest checksum

Checks the schema and canonical SHA-256 digest of an H/M AI transparency deployment manifest. It does not authenticate an issuer or certify legal compliance.

Input parameters:

- `manifest` (object, required): H/M AI transparency deployment manifest JSON.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/net-hogarmas-ai-transparency/mcp-ai-transparency#diagnostics

## Score history

- 2026-08-03: 67
- 2026-08-02: 67
- 2026-08-01: 66

## Links

- Remote endpoint: https://agents.hogarmas.net/mcp/ai-transparency
- Website: https://hogarmas.net/ai-transparency/
- Changelog RSS feed: https://verifymcp.io/servers/net-hogarmas-ai-transparency/mcp-ai-transparency/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/net-hogarmas-ai-transparency/mcp-ai-transparency/changelog.json
- HTML version of this page: https://verifymcp.io/servers/net-hogarmas-ai-transparency/mcp-ai-transparency