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.
Available components
Last scanned (9 hours ago)
Scores higher than 70% of PyPI servers
Category Security
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. How we score → Why this is hard to score →
Supply Chain Security49
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 3 of 10 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to presidio-v/presidio-hardened-ikigov-assess). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 10 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability66
- AI-judged instruction clarity (good).Pass
- 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. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management80
- Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 4 Nov 26 −3
- Stability: pass → 0.77 functional
- 29 Oct 26 0
- Stability: 0.97 → pass security
- 28 Oct 26 +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.
- 26 Oct 26 +16
- Malware scan: unverified → pass ▲ security
- 25 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- Stability: 0.83 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
- Package version: 0.29.0 → 0.29.1 functional
- 24 Oct 26 +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.
- 22 Oct 26 +16
- Malware scan: unverified → pass ▲ security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed pypi/presidio-hardened-ikigov-assess@0.29.1
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | presidio-v/presidio-hardened-ikigov-assess |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/presidio-v/presidio-hardened-ikigov-assess/.github/workflows/publish.yml@refs/tags/v0.29.1 |
| Rekor log index | 3469727979 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:3936920de33ce7e6d0d8146d7fedf95c01ab5d10420bf6a22bedd493fb678a22 |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 10 packages
| Packages resolved | 10 |
|---|---|
| Stale | 3 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
iga_assess ~208
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.
| Name | Type | Req | Description |
|---|---|---|---|
| affirmed | – | – | – |
| lang | string | – | – |
| risk_class | string | – | – |
| skipped | – | – | – |
| strict | boolean | – | – |
| use_case | string | – | – |
No output schema declared.
No examples provided.
iga_assess_with_evidence ~209
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.
| Name | Type | Req | Description |
|---|---|---|---|
| affirmed | – | – | – |
| evidence | – | – | – |
| lang | string | – | – |
| require_evidence | boolean | – | – |
| risk_class | string | – | – |
| skipped | – | – | – |
| strict | boolean | – | – |
| trust | – | – | – |
| use_case | string | – | – |
No output schema declared.
No examples provided.
iga_check_gate ~149
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.
| Name | Type | Req | Description |
|---|---|---|---|
| affirmed | – | – | – |
| gate | string | yes | – |
| lang | string | – | – |
| risk_class | string | – | – |
| skipped | – | – | – |
| strict | boolean | – | – |
No output schema declared.
No examples provided.
iga_euaiact_gap ~146
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).
| Name | Type | Req | Description |
|---|---|---|---|
| affirmed | – | – | – |
| lang | string | – | – |
| skipped | – | – | – |
| strict | boolean | – | – |
| use_case | string | – | – |
No output schema declared.
No examples provided.
iga_framework_info ~88
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.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | – |
No output schema declared.
No examples provided.
iga_iso_gap ~120
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).
| Name | Type | Req | Description |
|---|---|---|---|
| affirmed | – | – | – |
| lang | string | – | – |
| risk_class | string | – | – |
| skipped | – | – | – |
| use_case | string | – | – |
No output schema declared.
No examples provided.
iga_list_checklist ~109
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``.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | – |
No output schema declared.
No examples provided.
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.
pypi · presidio-hardened-ikigov-assess
claude mcp add presidio-v-presidio-hardened-ikigov-assess -- uvx presidio-hardened-ikigov-assess
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.