# Sovereign AI Act MCP

> Sovereign AI Act MCP, an MCP server by regulatoryai.eu, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Classify any AI system under the EU AI Act: risk tier + binding Articles, verbatim from the law.

- Canonical: https://www.anchorterminal.com/tools/regulatoryai-sovereign-ai-act-mcp
- Markdown: https://www.anchorterminal.com/tools/regulatoryai-sovereign-ai-act-mcp.md (~900 tokens)
- Slim: https://www.anchorterminal.com/tools/regulatoryai-sovereign-ai-act-mcp.min.md (~830 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/tools/regulatoryai-sovereign-ai-act-mcp.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-04

# Sovereign AI Act MCP

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by regulatoryai.eu (https://www.regulatoryai.eu/mcp/)
- Listed because: It's published in the registry under regulatoryai.eu, a namespace the registry only gives to whoever proves they control that domain.
- What the official MCP registry says: Classify any AI system under the EU AI Act: risk tier + binding Articles, verbatim from the law.

## Facts

- MCP registry: `eu.regulatoryai/sovereign-ai-act-mcp` 1.4.1
- Endpoint: https://www.regulatoryai.eu/mcp (streamable HTTP)
- Package: npm `sovereign-ai-act-mcp` (stdio)
- Source: https://github.com/saidbazyar/sovereign-ai-act-mcp
- Website: https://www.regulatoryai.eu/mcp/
- npm downloads a week: 69
- GitHub stars: 0
- Registry entry updated: 2026-09-23

## Tools

- Tools it lists (5, about 498 tokens of context, `tools/list` without credentials, checked 2026-10-04 22:25 UTC):
  - `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…
  - `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…
- How its tools read to an agent (0 errors, 9 warnings, 1 note, about 498 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score):
  - warn TC11 classify_ai_system: 1 parameter without a description: language
  - warn TC11 lookup_article: none of its 2 parameters has a description
  - warn TC11 review_feature: 1 parameter without a description: language
  - warn TC11 search_eu_ai_act: none of its 2 parameters has a description
  - warn TC16 classify_ai_system: no readOnlyHint or destructiveHint
  - warn TC16 get_compliance_deadlines: no readOnlyHint or destructiveHint
  - warn TC16 lookup_article: no readOnlyHint or destructiveHint
  - warn TC16 review_feature: no readOnlyHint or destructiveHint
  - warn TC16 search_eu_ai_act: no readOnlyHint or destructiveHint
  - note TC24 server: 5 of 5 tools have no outputSchema

- JSON: https://www.anchorterminal.com/api/v1/tools/regulatoryai-sovereign-ai-act-mcp.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming