Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Sovereign AI Act MCP

NPM · SOVEREIGN-AI-ACT-MCP · 2 COMPONENTS

Classify any AI system under the EU AI Act: risk tier + binding Articles, verbatim from the law.

0 this week 84 Trust /100

Last scanned (14 hours ago)

Scores higher than 75% of npm servers

Category Security

Trust breakdown (7 categories)

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 Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 92 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability73
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 847 tokens (~211/item across 4 items; 4 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 Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

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.

  • 19 Nov 26 +1
    • Stability: 0.97 → pass security
  • 18 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 12 Nov 26 +1
    • Stability: 0.97 → pass security
  • 10 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Nov 26 +5
    • Source repository: unverified → pass ▲ security
  • 8 Nov 26 −4
    • Provenance: pass → unverified ▼ security
  • 6 Nov 26 −3
    • Stability: pass → 0.80 functional
  • 31 Oct 26 +1
    • Stability: 0.97 → pass security
Diagnostics

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 21 Nov 2026 · Analysed npm/sovereign-ai-act-mcp@1.4.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 92 packages
Packages resolved 92
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 4 exposed · ~847 tokens

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 →

Tool Tokens
classify_ai_system ~288

Classify an AI system under the EU AI Act (Regulation (EU) 2024/1689 as amended by Regulation (EU) 2026/1744). Give a plain-language description of what the system does and it returns the risk tier (prohibited / high_risk / limited / minimal), the exact Annex III category where applicable, and the binding Articles — every reference grounded verbatim in the law. USE THIS when the user asks whether an AI system is high-risk or prohibited, what obligations apply to it, or which Articles bind a specific AI use-case. For looking up one known Article use lookup_article; for keyword search use search_eu_ai_act.

NameTypeReqDescription
descriptionstringyesPlain-language description of the AI system: what it does, who it affects, and the context of use. The more specific, the more precise the classification.
fullboolean–When true, include the verbatim cited Article/Annex text in the response (longer). When false (default), return the classification and references only.
languagestring–Language for the answer, as an ISO 639-1 code — one of the EU AI Act's 24 official languages (e.g. 'en' English, 'de' German, 'fr' French, 'es' Spanish, 'sv' Swedish). Defaults to 'en'.

No output schema declared.

No examples provided.

get_compliance_deadlines ~110

Return the canonical EU AI Act application timeline (the staggered dates each obligation starts to apply, as amended by Regulation (EU) 2026/1744, the Digital Omnibus on AI, in force 27 July 2026) together with the penalty/fine tiers under Article 99. Takes no arguments. USE THIS when the user asks when the EU AI Act (or a specific obligation) applies, what the key compliance deadlines are, or how large the fines can be.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

lookup_article ~218

Return the verbatim text of one specific EU AI Act Article (1–113), exactly as published in the Official Journal of the EU. USE THIS when the user names or asks for a known Article number (e.g. 'show me Article 6', 'what does Article 5 say'). For keyword/topic search across the whole law use search_eu_ai_act; to classify a system use classify_ai_system.

NameTypeReqDescription
languagestring–Language for the answer, as an ISO 639-1 code — one of the EU AI Act's 24 official languages (e.g. 'en' English, 'de' German, 'fr' French, 'es' Spanish, 'sv' Swedish). Defaults to 'en'.
numberintegeryesThe Article number to retrieve, an integer from 1 to 113. Examples: 5 (prohibited practices), 6 (high-risk classification), 9 (risk management), 14 (human oversight), 50 (transparency), 99 (penalties…

No output schema declared.

No examples provided.

search_eu_ai_act ~231

Full-text keyword search across the entire EU AI Act corpus — all Articles (1–113), Recitals (1–180) and Annexes (I–XIII) — returning the provisions that match your terms, each grounded verbatim in the law. USE THIS when you want to find where a topic, term or obligation is addressed but do not know the Article number (e.g. 'where does the law cover human oversight?', 'find biometric categorisation', 'rules for GPAI'). To fetch one known Article use lookup_article; to assess a specific system's risk tier use classify_ai_system.

NameTypeReqDescription
languagestring–Language for the answer, as an ISO 639-1 code — one of the EU AI Act's 24 official languages (e.g. 'en' English, 'de' German, 'fr' French, 'es' Spanish, 'sv' Swedish). Defaults to 'en'.
querystringyesKeyword(s) or short phrase to search for across the EU AI Act. Use legal/topic terms rather than full questions for best matches.

No output schema declared.

No examples provided.

Install

How do I install the Sovereign AI Act MCP server?

Sovereign AI Act MCP runs locally as an npm package, launched with npx -y sovereign-ai-act-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · sovereign-ai-act-mcp

# add to Claude Code
claude mcp add eu-regulatoryai-sovereign-ai-act-mcp -- npx -y sovereign-ai-act-mcp
Common questions

What is the Sovereign AI Act MCP server?

Sovereign AI Act MCP is listed in the public MCP registry as eu.regulatoryai/sovereign-ai-act-mcp. Classify any AI system under the EU AI Act: risk tier + binding Articles, verbatim from the law. This page covers its npm package (sovereign-ai-act-mcp).

Is the Sovereign AI Act MCP server safe to use?

Sovereign AI Act MCP scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. 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 Sovereign AI Act MCP server expose?

Sovereign AI Act MCP exposes 4 tools: classify_ai_system, lookup_article, search_eu_ai_act, get_compliance_deadlines. Their descriptions and schemas cost roughly 847 tokens of context every time the server is loaded.

Is the Sovereign AI Act MCP server still maintained?

Sovereign AI Act MCP is still listed as active in the MCP registry. We last reached this channel on 21 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 Sovereign AI Act MCP server under?

Sovereign AI Act MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the Sovereign AI Act MCP server?

VerifyMCP ran 16 checks on Sovereign AI Act MCP, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.