# io.github.presidio-v/presidio-hardened-ikigov-assess (pypi · presidio-hardened-ikigov-assess)

IKI-Gov AI governance assessment: score AI use cases, check quality gates G0-G5, map to EU AI Act.

- Trust score: 73/100 (medium)
- Change this week: −18
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- pypi · `presidio-hardened-ikigov-assess`: 73/100 (this document), [markdown](https://verifymcp.io/servers/presidio-v-presidio-hardened-ikigov-assess/presidio-hardened-ikigov-assess.md), [page](https://verifymcp.io/servers/presidio-v-presidio-hardened-ikigov-assess/presidio-hardened-ikigov-assess)

## Channel facts

- Registry: `pypi`
- Package: `presidio-hardened-ikigov-assess`
- Version: `0.29.1`
- 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 2026-11-05.

- **Supply Chain Security**: 49/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 3 of 10 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to presidio-v/presidio-hardened-ikigov-assess).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 10 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1200 tokens (~171/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 80/100
  - Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the io.github.presidio-v/presidio-hardened-ikigov-assess MCP server?

io.github.presidio-v/presidio-hardened-ikigov-assess runs locally as a PyPI package, launched with uvx presidio-hardened-ikigov-assess. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add presidio-v-presidio-hardened-ikigov-assess -- uvx presidio-hardened-ikigov-assess
```

### Cursor

```json
{
  "mcpServers": {
    "presidio-v-presidio-hardened-ikigov-assess": {
      "command": "uvx",
      "args": [
        "presidio-hardened-ikigov-assess"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "presidio-v-presidio-hardened-ikigov-assess": {
      "command": "uvx",
      "args": [
        "presidio-hardened-ikigov-assess"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add presidio-v-presidio-hardened-ikigov-assess -- uvx presidio-hardened-ikigov-assess
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "presidio-v-presidio-hardened-ikigov-assess": {
      "type": "local",
      "command": [
        "uvx",
        "presidio-hardened-ikigov-assess"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add presidio-v-presidio-hardened-ikigov-assess --command uvx --arg presidio-hardened-ikigov-assess
```

### Hermes

```yaml
mcp_servers:
  presidio-v-presidio-hardened-ikigov-assess:
    command: "uvx"
    args: ["presidio-hardened-ikigov-assess"]
```

### Netclaw

```json
{
  "McpServers": {
    "presidio-v-presidio-hardened-ikigov-assess": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "presidio-hardened-ikigov-assess"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add presidio-v-presidio-hardened-ikigov-assess -t stdio -c uvx -a presidio-hardened-ikigov-assess
```

### Other

```json
{
  "mcpServers": {
    "presidio-v-presidio-hardened-ikigov-assess": {
      "command": "uvx",
      "args": [
        "presidio-hardened-ikigov-assess"
      ]
    }
  }
}
```

## 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.

### 2026-11-05 (score 73, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-04 (score 88, −3)

- [functional] Stability: pass → 0.77

### 2026-10-29 (score 91, 0)

- [security] Stability: 0.97 → pass

### 2026-10-28 (score 91, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 90, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-10-25 (score 74, −15)

- [security regression] Malware scan: pass → unverified
- [security regression] Stability: 0.83 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.29.0 → 0.29.1

### 2026-10-24 (score 89, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 88, +16)

- [security improvement] Malware scan: unverified → pass

## MCP tools (7)

### `iga_framework_info` (~88 tokens)

Describe the IKI-Gov reference model.

Returns the lifecycle phases, measurement dimensions (M1–M6), lifecycle
gates (G0–G5) with their transitions, checklist sections, and risk
classes — all localised to ``lang`` (de|en). Call this first to learn
the vocabulary used by the other tools.

Input parameters:

- `lang` (string)

### `iga_list_checklist` (~109 tokens)

List the 25 IKI-Gov checklist items.

Each item carries its ID (e.g. ``S1``, ``D3``, ``T4``), the question
text in ``lang`` (de|en), its primary M-dimension, the gates it gates,
and its section. Use the returned IDs as the ``affirmed``/``skipped``
arguments to ``iga_assess`` and ``iga_check_gate``.

Input parameters:

- `lang` (string)

### `iga_assess` (~208 tokens)

Assess an AI use case against the IKI-Gov checklist.

\``affirmed`` is the list of checklist item IDs the organisation can
evidence (e.g. ``["S1", "S2", "D1"]``); ``skipped`` lists IDs marked
not-applicable (excluded from scoring). Any item neither affirmed nor
skipped counts as denied. ``risk_class`` is low|medium|high and scales
item weights; ``lang`` is de|en. ``strict`` (implied at high risk) makes
skipped gate-critical items block their gate. Returns per-dimension
M1–M6 scores, overall maturity, and gate readiness, where a gate is
OPEN/PARTIAL/BLOCKED under the active risk policy.

Input parameters:

- `affirmed`
- `lang` (string)
- `risk_class` (string)
- `skipped`
- `strict` (boolean)
- `use_case` (string)

### `iga_assess_with_evidence` (~209 tokens)

Assess a use case, affirming items backed by signed evidence references.

\``evidence`` is a list of EvidenceRef objects emitted by a peer
\``presidio-hardened-*`` control (e.g. ``presidio-hardened-ai``); ``trust``
maps signer id to verification key. Items carrying valid evidence are
affirmed (under ``require_evidence``, only those that verify against
\``trust``), and the result adds per-item ``provenance`` (self |
evidence | evidence-verified) plus an ``evidence_coverage`` block. Lets an
agent chain a control's evidence straight into an IKI-Gov assessment.

Input parameters:

- `affirmed`
- `evidence`
- `lang` (string)
- `require_evidence` (boolean)
- `risk_class` (string)
- `skipped`
- `strict` (boolean)
- `trust`
- `use_case` (string)

### `iga_check_gate` (~149 tokens)

Check readiness for one IKI-Gov lifecycle gate (``gate``: G0–G5).

Returns the gate's transition label and status under the active risk
policy: OPEN (every mapped item affirmed; at low risk, skips are
forgiven), PARTIAL (only gaps are skips, at medium risk), or BLOCKED
(any mapped item denied, or — under ``strict``/high risk — skipped).
\``blocking_skips`` lists skips that block the gate under strict policy.

Input parameters:

- `affirmed`
- `gate` (string, required)
- `lang` (string)
- `risk_class` (string)
- `skipped`
- `strict` (boolean)

### `iga_iso_gap` (~120 tokens)

Map an assessment to ISO/IEC 42001 clause-level coverage.

Returns each ISO/IEC 42001 clause group (4–10 + Annex A) as covered /
partial / gap based on the affirmed checklist items, with the count of
affirmed-vs-total mapped items and the outstanding item IDs per clause.
Skipped and denied items count as not affirmed (no coverage credit).

Input parameters:

- `affirmed`
- `lang` (string)
- `risk_class` (string)
- `skipped`
- `use_case` (string)

### `iga_euaiact_gap` (~146 tokens)

Map an assessment to EU AI Act high-risk obligations (Art. 9–18, 72).

For high-risk systems only: returns each article (9, 10, 11, 12, 13, 14,
15, 17) as OPEN / PARTIAL / BLOCKED based on the readiness of the gates
that generate its evidence, with the per-article gate statuses and the
outstanding (non-OPEN) gates. Gates are evaluated at high risk (strict).

Input parameters:

- `affirmed`
- `lang` (string)
- `skipped`
- `strict` (boolean)
- `use_case` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/presidio-v-presidio-hardened-ikigov-assess/presidio-hardened-ikigov-assess#diagnostics

## Score history

- 2026-11-05: 73
- 2026-11-04: 88
- 2026-11-03: 91
- 2026-11-02: 91
- 2026-11-01: 91
- 2026-10-31: 91
- 2026-10-30: 91
- 2026-10-29: 91
- 2026-10-28: 91
- 2026-10-27: 90
- 2026-10-26: 90
- 2026-10-25: 74
- 2026-10-24: 89
- 2026-10-23: 88
- 2026-10-22: 88
- 2026-10-21: 72
- 2026-10-20: 72
- 2026-10-19: 71
- 2026-10-18: 71
- 2026-10-17: 85
- 2026-10-16: 85
- 2026-10-15: 69
- 2026-10-14: 84
- 2026-10-13: 84
- 2026-10-12: 83
- 2026-10-08: 62
- 2026-10-04: 62
- 2026-10-03: 62
- 2026-10-02: 62
- 2026-10-01: 62

## Common questions

### What is the io.github.presidio-v/presidio-hardened-ikigov-assess MCP server?

io.github.presidio-v/presidio-hardened-ikigov-assess is an MCP server listed in the public MCP registry as io.github.presidio-v/presidio-hardened-ikigov-assess. IKI-Gov AI governance assessment: score AI use cases, check quality gates G0-G5, map to EU AI Act. This page covers its PyPI package (presidio-hardened-ikigov-assess).

### Is the io.github.presidio-v/presidio-hardened-ikigov-assess MCP server safe to use?

io.github.presidio-v/presidio-hardened-ikigov-assess scores 73 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.presidio-v/presidio-hardened-ikigov-assess MCP server expose?

io.github.presidio-v/presidio-hardened-ikigov-assess exposes 7 tools: iga_framework_info, iga_list_checklist, iga_assess, iga_assess_with_evidence, iga_check_gate, and 2 more. Their descriptions and schemas cost roughly 1,029 tokens of context every time the server is loaded.

### Is the io.github.presidio-v/presidio-hardened-ikigov-assess MCP server still maintained?

io.github.presidio-v/presidio-hardened-ikigov-assess is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.presidio-v/presidio-hardened-ikigov-assess MCP server under?

io.github.presidio-v/presidio-hardened-ikigov-assess declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/presidio-hardened-ikigov-assess/
- Socket report: https://socket.dev/pypi/package/presidio-hardened-ikigov-assess
- Repository: https://github.com/presidio-v/presidio-hardened-ikigov-assess
- Changelog RSS feed: https://verifymcp.io/servers/presidio-v-presidio-hardened-ikigov-assess/presidio-hardened-ikigov-assess.xml
- Changelog JSON feed: https://verifymcp.io/servers/presidio-v-presidio-hardened-ikigov-assess/presidio-hardened-ikigov-assess.json
- HTML version of this page: https://verifymcp.io/servers/presidio-v-presidio-hardened-ikigov-assess/presidio-hardened-ikigov-assess