Skip to content
Sovereign AI Act logo

Sovereign AI Act MCP server

Which MCP servers are Sovereign AI Act's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-19

← Back to Sovereign AI Act

Whose server it is
  • Registry nameeu.regulatoryai/sovereign-ai-act-mcpverified in the MCP registry

The registry name sits under regulatoryai.eu. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-19
  • Stateanswerschecked 2026-10-19
  • Tools5
  • Server calls itselfsovereign-ai-act
  • Server version1.4.1
  • Protocol version2025-06-18

On 2026-10-19 the server answered initialize and tools/list without a sign-in. First answer in 36 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.

Once connected

  • For "Classify an AI system by EU AI Act risk tier", the likely first call is classify_ai_system.
  • Parameters are untyped or undescribed in 4 of 5 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 9, the first on 2026-10-19
  • INITE MCP score82 of 100answers 100 · definitions 70 · context 100 · use 25 · connects 100
  • Use17 npm downloads a week
  • Answered100% of days9 of 9 daily checks
  • Median first answer113 ms
  • Space in an agent's context≈ 499 tokensthe definitions of all its tools (5), which an agent carries on every turn
  • Tool definitionsC · 70 of 100
  • Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 4 of 5
  • Not saying whether it only reads or can destroy: 5 of 5

What an agent can do with it

  • can do · Classify an AI system by EU AI Act risk tier
  • not sure · Check which EU AI Act articles bind a given AI system
  • not sure · Run AI compliance due diligence on an acquisition target

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers5 tools · read 2026-10-19
  • classify_ai_system

    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…

  • lookup_article

    Verbatim text of an original EU AI Act Article (1–113) or inserted Article 4a, 60a or 75a–75d.

  • search_eu_ai_act

    Full-text search across the EU AI Act corpus (Articles, Recitals, Annexes).

  • get_compliance_deadlines

    Canonical EU AI Act application dates (post Digital-Omnibus) + fine tiers.

  • review_feature

    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…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "sovereign-ai-act-mcp": {
      "type": "http",
      "url": "https://www.regulatoryai.eu/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

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

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://www.regulatoryai.eu/mcp as a custom connector in the settings.

Also shipped through: npm

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.