disclos-eu-ai-act
# disclos-eu-ai-act
An **MCP server** that lets AI assistants (Claude Desktop, Claude Code, Cursor,
Windsurf, and any MCP-compatible client) classify an AI system under the
**EU AI Act** — Regulation (EU) 2024/1689.
Ask your assistant a plain-English question and it returns a structured
**scope finding**: the risk tier, the obligations, and the deadlines.
> Built and maintained by [Disclos](https://disclos.eu) — fixed-price EU AI Act
> audits for SaaS companies.
---
## What it does
Four tools:
| Tool | What it returns |
|------|-----------------|
| `classify_ai_system` | A full scope finding — tier, obligations, deadline, and the exact EUR-Lex article — from a description of the product. |
| `eu_ai_act_timeline` | The enforcement timeline (Feb 2025 → Aug 2028) and what takes effect on each date. |
| `explain_tier` | A detailed explanation of one risk tier and its duties. |
| `framework_crosswalk` | Maps an EU AI Act tier to the equivalent controls in **ISO/IEC 42001**, **NIST AI RMF**, and **GDPR**. |
It tests every tier the Act defines: **prohibited (Art 5)**, **high-risk
(Annex III)**, **GPAI provider (Art 53)**, **transparency (Art 50)**,
**minimal**, and **out of scope** — flags the common mistake of
**over-classifying** as high-risk, and links every finding to the official
**EUR-Lex** text.
## TL;DR — 60-second install (Claude Desktop)
Add this to your Claude Desktop config
(`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS):
```json
{
"mcpServers": {
"disclos-eu-ai-act": {
"command": "npx",
"args": ["-y", "github:GatisOzols/disclos-eu-ai-act"]
}
}
}
```
Restart Claude Desktop, then ask:
> "We run a B2B SaaS with an AI chatbot and some EU customers. Are we in scope
> under the EU AI Act, and at what tier?"
Claude calls `classify_ai_system` and returns a finding with the tier,
obligations, and the relevant deadline.
## Run from source
```bash
git clone https://github.com/GatisOzols/disclos-eu-ai-act
cd disclos-eu-ai-act
npm install
npm start # starts the server on stdio
```
Then point any MCP client at `node /path/to/src/index.js`.
## How it works
A small, deterministic classifier maps six yes/no facts about your product to
the Act's tiers. No network calls, no data collection, no tracking — everything
runs locally on stdio.
## Accuracy & limits
- The logic follows the public text of Articles 5, 6, 50, 53 and Annex III.
- It's a screening aid, accurate for most straightforward SaaS products.
- Edge cases (multi-modal systems, mixed provider/deployer roles, biometric
inference) need a human review.
- **This is general information, not legal advice.**
## License
[MIT](LICENSE) © 2026 Gatis Ozols / Disclos. Original work, free to use, copy,
modify and share.
TDQS
Scored across 4 tools
The tools are mostly distinct: classify_ai_system maps user input to a risk tier, explain_tier describes a known tier, while timeline and crosswalk serve clear reference purposes. There is slight overlap between classify_ai_system and explain_tier (both return obligations and deadlines), but their primary functions differ enough to avoid confusion.
All names use snake_case, but the pattern is mixed: classify_ai_system and explain_tier are verb_noun, while eu_ai_act_timeline and framework_crosswalk are noun phrases. The inconsistency in starting part (verb vs. noun) makes the set slightly less predictable.
Four tools is well-scoped for an information-focused EU AI Act server. Each tool covers a specific high-level user need without redundancy, and the count is neither too thin nor excessive.
The set covers classification, timeline, tier explanations, and cross-framework mapping, which addresses common compliance questions. Minor gaps exist (e.g., no tool for searching specific legal provisions or compliance checklists), but the core workflows are covered and agents can work around these gaps.