Sovereign AI Act MCP

saidbazyar/sovereign-ai-act-mcp

Connects your AI agent to a deterministic classifier for the EU AI Act (Regulation 2024/1689) backed by the full legal text. Exposes four tools: classify_ai_system takes a plain-language AI description and returns risk tier (prohibited, high-risk, limited, minimal) plus the exact Annex III category and binding Articles; lookup_article fetches verbatim text of any Article 1 through 113; search_eu_ai_act runs full-text search across Articles, Recitals, and Annexes; get_compliance_deadlines returns application dates and fine tiers. Every answer cites the actual law instead of hallucinating compliance advice. Runs against a free API at regulatoryai.eu with no key required. Reach for this when you need to answer "is my system high-risk?" with an auditable legal reference.

tools: 5
transport: STDIO, HTTP
last updated: Sep 23, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://www.regulatoryai.eu/mcp --name sovereign-ai-act-mcp

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

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

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 5 tools

Verified live against the running server on Nov 6, 2026.

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 in the law. Use whenever asked if an AI system is high-risk/prohibited or what obligations apply.2 params

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.

Parameters* required

description*string

Plain-language description of the AI system.

languagestring

default: en

lookup_articleVerbatim text of an original EU AI Act Article (1–113) or inserted Article 4a, 60a or 75a–75d.2 params

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

Parameters* required

languagestring

default: en

number*value

search_eu_ai_actFull-text search across the EU AI Act corpus (Articles, Recitals, Annexes).2 params

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

Parameters* required

languagestring

default: en

query*string

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

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

No parameters. Call it with no arguments.

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 binding Articles, the obligations that apply, red flags and concrete next steps — grounded verba...2 params

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 verba...

Parameters* required

input*string

The AI feature, spec or behaviour you are about to build/ship.

languagestring

default: en

Readme

◆ 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

View the full README on GitHub

Details

Repository: github.com/saidbazyar/sovereign-ai-act-mcp
Website: www.regulatoryai.eu/mcp
Package: sovereign-ai-act-mcp
Transport: STDIO, HTTP
Registry: MCP registry, active
Tools verified: Nov 6, 2026