# services.gera/mcp-gera-compliance (npm · @gera-services/mcp-gera-compliance)

Classify AI systems under the EU AI Act and look up obligations and articles. Offline, no auth.

- Trust score: 54/100 (low)
- Change this week: +21
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@gera-services/mcp-gera-compliance`: 54/100 (this document), [markdown](https://verifymcp.io/servers/services-gera-mcp-gera-compliance/gera-services-mcp-gera-compliance.md), [page](https://verifymcp.io/servers/services-gera-mcp-gera-compliance/gera-services-mcp-gera-compliance)

## Channel facts

- Registry: `npm`
- Package: `@gera-services/mcp-gera-compliance`
- Version: `1.0.1`
- 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**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 40 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 778 tokens (~194/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 70/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 9% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add services-gera-mcp-gera-compliance -- npx -y @gera-services/mcp-gera-compliance
```

### Codex

```bash
codex mcp add services-gera-mcp-gera-compliance -- npx -y @gera-services/mcp-gera-compliance
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add services-gera-mcp-gera-compliance --command npx --arg -y --arg @gera-services/mcp-gera-compliance
```

### Hermes

```yaml
mcp_servers:
  services-gera-mcp-gera-compliance:
    command: "npx"
    args: ["-y", "@gera-services/mcp-gera-compliance"]
```

### Other

```json
{
  "mcpServers": {
    "services-gera-mcp-gera-compliance": {
      "command": "npx",
      "args": [
        "-y",
        "@gera-services/mcp-gera-compliance"
      ]
    }
  }
}
```

## 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 54, +7)

- [security regression] Install scripts: pass → unverified
- [security regression] Provenance: fail → unverified
- [security improvement] Known CVEs: unverified → partial
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Maintenance: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] License: pass → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: MIT

### 2026-08-01 (score 47, −10)

- [security regression] Known CVEs: partial → unverified
- [functional regression] Dependency health: partial → unverified

### 2026-07-31 (score 57, +48)

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

### 2026-07-30 (score 9, −56)

- [security regression] Known CVEs: partial → unverified
- [security regression] Malware scan: pass → unverified
- [functional regression] Dependency health: partial → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-07-29 (score 65, +46)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: MIT

### 2026-07-28 (score 19, −14)

- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 33)

First indexed and scored.

## MCP tools (4)

### `classify_ai_system` (~540 tokens)

Classify an AI system under the EU AI Act

Run the EU AI Act risk classification on an AI system using the Gera deterministic decision tree (Articles 5, 6(1), 6(2), 6(3), 50). Pass the boolean answer keys that apply to the system (omit a key to mean "no"/unknown). Returns the risk tier (prohibited | high_risk | borderline | limited_risk | minimal_risk), the triggered articles, the obligations, and the full reasoning trace. This is deterministic and offline — same result the GeraCompliance product gives.

Input parameters:

- `annex1_safety_component_regulated_product` (boolean)
- `annex3_biometric_identification_permitted` (boolean)
- `annex3_critical_infrastructure` (boolean)
- `annex3_education_assessment` (boolean)
- `annex3_employment_recruitment` (boolean)
- `annex3_essential_services_access` (boolean)
- `annex3_justice_democratic_process` (boolean)
- `annex3_law_enforcement` (boolean)
- `annex3_migration_border_control` (boolean)
- `art5_criminal_prediction_profiling` (boolean)
- `art5_emotion_detection_workplace_education` (boolean)
- `art5_exploits_vulnerabilities` (boolean)
- `art5_facial_image_scraping` (boolean)
- `art5_realtime_remote_biometric_id_law_enforcement` (boolean)
- `art5_sensitive_attribute_inference` (boolean)
- `art5_social_scoring_public_authority` (boolean)
- `art5_subliminal_manipulation` (boolean)
- `art6_3_detects_patterns_not_replacing_human` (boolean)
- `art6_3_improves_prior_human_activity` (boolean)
- `art6_3_materially_influences_decisions` (boolean)
- `art6_3_merely_prepares_decisions` (boolean)
- `art6_3_narrow_procedural_task` (boolean)
- `art6_3_preparatory_task` (boolean)
- `art6_3_significant_risk_health_safety_rights` (boolean)
- `cat4_m1_narrows_opportunities` (boolean)
- `cat4_m2_override_impractical` (boolean)
- `cat4_m3_contractual_input` (boolean)
- `limited_risk_direct_user_interaction_no_disclosure` (boolean)
- `limited_risk_generates_synthetic_media` (boolean)

### `get_requirements` (~66 tokens)

Get EU AI Act requirements for a risk tier

Return the compliance obligations, key articles, and whether a conformity assessment is required for a given EU AI Act risk tier. Use after classify_ai_system, or directly when the tier is already known.

Input parameters:

- `risk_tier` (string, required): The EU AI Act risk tier to look up.

### `get_regulation_info` (~117 tokens)

Look up an EU AI Act article

Look up a specific EU AI Act article by number (e.g. "5", "6", "14", "50", "99"), or search all articles by keyword (e.g. "biometric", "transparency", "penalties"). Returns the article title, a practitioner summary, and which risk tiers it applies to. Omit both arguments to list every available article.

Input parameters:

- `article` (string): Article number, e.g. "14".
- `keyword` (string): Keyword to search article titles and summaries.

### `list_risk_triggers` (~55 tokens)

List EU AI Act risk triggers (prohibited + high-risk)

List the eight Article 5 prohibited practices and the eight Annex III high-risk categories, each with the boolean answer key used by classify_ai_system. Use this to map a plain-language system description onto the correct classification inputs.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/services-gera-mcp-gera-compliance/gera-services-mcp-gera-compliance#diagnostics

## Score history

- 2026-08-03: 54
- 2026-08-02: 54
- 2026-08-01: 47
- 2026-07-31: 57
- 2026-07-30: 9
- 2026-07-29: 65
- 2026-07-28: 19
- 2026-07-27: 33

## Links

- npm package: https://www.npmjs.com/package/@gera-services/mcp-gera-compliance
- Socket report: https://socket.dev/npm/package/@gera-services/mcp-gera-compliance
- Website: https://geracompliance.com/
- Changelog RSS feed: https://verifymcp.io/servers/services-gera-mcp-gera-compliance/gera-services-mcp-gera-compliance/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/services-gera-mcp-gera-compliance/gera-services-mcp-gera-compliance/changelog.json
- HTML version of this page: https://verifymcp.io/servers/services-gera-mcp-gera-compliance/gera-services-mcp-gera-compliance