Skip to content

Sovereign AI Act MCP server

eu.regulatoryai/sovereign-ai-act-mcpregulatoryai.eustreamable-httpv1.4.1Scanned

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

5 tools: 2 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 2 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Sovereign AI Act MCP server can do

The Sovereign AI Act MCP server is published by regulatoryai.eu, a domain the MCP Registry verified. It has 5 tools. It can create or change data (2 tools: classify_ai_system and review_feature), but cannot delete data. 3 tools only read.

1 tool brings in text other people can write (get_compliance_deadlines).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 11, 2026, version 1.4.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

5 tools

Changes things 2Claude Code: ask
  • classify_ai_systemClassify an AI system under the EU AI Act (Regulation (EU) 2024/1689): risk tier (prohibited/high_risk/limited/minimal) + Annex III category + binding Articles, grounded verbatim i…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Classify an AI system under the EU AI Act (Regulation (EU) 2024/1689): risk tier (prohibited/high_risk/limited/minimal) + Annex III category + binding Articles, grounded verbatim in the law. Use whenever asked if an AI system is high-risk/prohibited or what obligations apply.
  • review_featureEU AI Act CO-PILOT review for builders: pass a feature, spec or behaviour you are about to ship and get a ship/caution/stop signal (OK / TRANSPARENCY / REVIEW REQUIRED / STOP), the…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    EU AI Act CO-PILOT review for builders: pass a feature, spec or behaviour you are about to ship and get a ship/caution/stop signal (OK / TRANSPARENCY / REVIEW REQUIRED / STOP), the binding Articles, the obligations that apply, red flags and concrete next steps — grounded verbatim in Regulation (EU) 2024/1689. Use proactively while designing or coding an AI feature, before it ships.
Only reads 3Show 3 read-only tools
  • get_compliance_deadlinesCanonical EU AI Act application dates (post Digital-Omnibus) + fine tiers.Reads text others writeNo findings

    Why it is in this group

    • The name "get_compliance_deadlines" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
    Description, as the server wrote it
    Canonical EU AI Act application dates (post Digital-Omnibus) + fine tiers.
  • lookup_articleVerbatim text of an original EU AI Act Article (1–113) or inserted Article 4a, 60a or 75a–75d.No findings

    Why it is in this group

    • The name "lookup_article" says "lookup": a word for reading.
    Description, as the server wrote it
    Verbatim text of an original EU AI Act Article (1–113) or inserted Article 4a, 60a or 75a–75d.
  • search_eu_ai_actFull-text search across the EU AI Act corpus (Articles, Recitals, Annexes).No findings

    Why it is in this group

    • The name "search_eu_ai_act" says "search": a word for reading.
    Description, as the server wrote it
    Full-text search across the EU AI Act corpus (Articles, Recitals, Annexes).

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:53 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
2
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.regulatoryai.eu/mcp: tools/list returned 5 tools to an anonymous client, including classify_ai_system (write), review_feature (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.4.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http sovereign-ai-act https://www.regulatoryai.eu/mcp
claude mcp add --transport http sovereign-ai-act https://www.regulatoryai.eu/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__sovereign-ai-act__lookup_article",
      "mcp__sovereign-ai-act__search_eu_ai_act",
      "mcp__sovereign-ai-act__get_compliance_deadlines"
    ],
    "ask": [
      "mcp__sovereign-ai-act__classify_ai_system",
      "mcp__sovereign-ai-act__review_feature"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as sovereign-ai-act. Review it before you use it.

Capability tags behind 1 rule
  • mcp__sovereign-ai-act__get_compliance_deadlines untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/eu.regulatoryai/sovereign-ai-act-mcp/verify?hash=8e617c98de76ba5af10df314717c0c33d863f715d4017f4f3acfbbc39a31a8c8" | jq -e '.changed == false'

Pinned hash 8e617c98de76, from Nov 11, 2026, 12:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/eu.regulatoryai/sovereign-ai-act-mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for eu.regulatoryai/sovereign-ai-act-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/eu.regulatoryai/sovereign-ai-act-mcp.svg)](https://radar.anlyon.com/servers/eu.regulatoryai/sovereign-ai-act-mcp)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:12 UTC.

Sovereign AI Act MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Sovereign AI Act MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 2 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Sovereign AI Act MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Sovereign AI Act MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Sovereign AI Act MCP server have?

5 tools: 2 write, 3 read. classify_ai_system, review_feature, lookup_article, search_eu_ai_act and get_compliance_deadlines.

Does the Sovereign AI Act MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Sovereign AI Act MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Sovereign AI Act MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.