English Français العربية

Sovereign AI Act MCP

Official registry AI and agents

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

Source code Website Documentation

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)
Claude Code 
claude mcp add --transport http sovereign-ai-act-mcp 'https://www.regulatoryai.eu/mcp'
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "sovereign-ai-act-mcp": {
            "type": "http",
            "url": "https://www.regulatoryai.eu/mcp"
        }
    }
}
NPM package sovereign-ai-act-mcp
Claude Code 
claude mcp add sovereign-ai-act-mcp -- npx -y sovereign-ai-act-mcp@1.4.0
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "sovereign-ai-act-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "sovereign-ai-act-mcp@1.4.0"
            ]
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. ◆ Sovereign AI Act — MCP server
  2. 🛠️ Tools
  3. 🚀 Install (Claude Desktop)
  4. 🌐 Remote server (zero install)
  5. ⚡ Try the API directly (no install, no key)
  6. 💎 Why trust it
  7. ⚙️ Config

◆ Sovereign AI Act — MCP server

Give your AI agent a trustworthy EU AI Act expert.

This Model Context Protocol server exposes Leo — the deterministic classifier for Regulation (EU) 2024/1689 (the EU AI Act), as amended by Regulation (EU) 2026/1744 (the Digital Omnibus on AI, in force 27 July 2026) — as callable tools. Every answer is grounded verbatim in the official law. Leo never guesses.

When a user asks an AI "is my AI system high-risk under the EU AI Act?", the honest answer must cite the actual law — not a hallucination. This server lets your agent do exactly that.

🛠️ Tools

ToolWhat it does
classify_ai_systemPlain-language AI description → risk tier (prohibited / high-risk / limited / minimal) + the exact Annex III category and binding Articles.
lookup_articleVerbatim direct lookup for original Articles 1–113 plus inserted Articles 4a, 60a and 75a–75d.
search_eu_ai_actFull-text search across the original 2024 Articles, Recitals and Annexes.
get_compliance_deadlinesThe application dates in force under Regulation (EU) 2026/1744 (statuses computed at call time) and the Article 99 fine tiers.
review_featurePre-release review of an AI feature: signal, binding Articles, obligations, red flags and next steps.

🚀 Install (Claude Desktop)

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "sovereign-ai-act": {
      "command": "npx",
      "args": ["-y", "sovereign-ai-act-mcp"]
    }
  }
}

Restart Claude, then ask: "Is an AI that screens job applicants high-risk under the EU AI Act?" — Claude calls Leo and answers with the exact Articles.

Works the same in Cursor, VS Code, Windsurf, Cline, and any MCP-capable client.

🌐 Remote server (zero install)

Clients that support Streamable HTTP can use the same five tools directly:

https://www.regulatoryai.eu/mcp

⚡ Try the API directly (no install, no key)

curl -X POST https://www.regulatoryai.eu/api/classify \
  -H "content-type: application/json" \
  -d '{"description":"AI that screens job applicants and ranks CVs"}'
{
  "ok": true,
  "tier": "high_risk",
  "classifications": [{
    "tier": "high_risk",
    "rule": "Employment, recruitment & worker management (Annex III.4)",
    "annex": "III.4",
    "articles": [6, 9, 10, 11, 13, 14, 15],
    "severity": "HIGH — conformity assessment + risk management + ..."
  }]
}

Also: GET /api/article/{1-113|4a|60a|75a|75b|75c|75d} · GET /api/annex/XIV/1 · GET /api/search?q=... (original 2024 corpus plus the listed 2026 insertions)

💎 Why trust it

  • Verbatim law. The original 2024 corpus contains 113 Articles, 180 Recitals and 13 Annexes. Inserted Articles 4a, 60a, 75a–75d and Annex XIV from Regulation (EU) 2026/1744 are published separately in all 24 languages.
  • Deterministic. A rule engine, not a guess — every verdict cites the Article that binds you.
  • EU-sovereign. Operated by Dominion Intelligence AB, hosted in the EU.
  • 24 languages. Ask in your own language.

⚙️ Config

  • SOVEREIGN_API_BASE — override the API base URL (default https://www.regulatoryai.eu).
  • No API key required.

Indicative classification grounded in the official text — not legal advice. Powered by **Sovereign AI Act** · © Dominion Intelligence AB

Frequently asked questions

What is Sovereign AI Act MCP?

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

How do I install Sovereign AI Act MCP?

It runs as a remote server. In Claude Code: claude mcp add --transport http sovereign-ai-act-mcp 'https://www.regulatoryai.eu/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does Sovereign AI Act MCP need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is Sovereign AI Act MCP open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains Sovereign AI Act MCP?

It is published by saidbazyar. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.