About Disclos — EU AI Act
Disclos — EU AI Act is an MCP server for screening AI systems against Regulation (EU) 2024/1689. It returns risk tiers, obligations, and deadlines with links to EUR-Lex, while noting that edge cases require human review.
Key features
- 01Classify AI systems by risk tier
- 02Return obligations and deadlines
- 03Show the enforcement timeline
- 04Explain tier-specific duties
- 05Crosswalk to ISO 42001, NIST AI RMF, and GDPR
- 06Link findings to EUR-Lex
Use cases
- 01Screen a SaaS product for EU AI Act scope
- 02Check duties and dates for a risk tier
- 03Compare EU AI Act controls with other frameworks
MCP support
Exposes four tools to MCP clients: classify_ai_system, eu_ai_act_timeline, explain_tier, and framework_crosswalk. The server can run locally over stdio.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.disclos.euclaude mcp add --transport http disclos-eu-ai-act https://mcp.disclos.eu{"mcpServers":{"disclos-eu-ai-act":{"type":"http","url":"https://mcp.disclos.eu"}}}Open in Cursor{"servers":{"disclos-eu-ai-act":{"type":"http","url":"https://mcp.disclos.eu"}}}Open in VS Code{"mcpServers":{"disclos-eu-ai-act":{"type":"http","url":"https://mcp.disclos.eu"}}}{"mcpServers":{"disclos-eu-ai-act":{"serverUrl":"https://mcp.disclos.eu"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
4| Parameter | Type | Required | Description |
|---|---|---|---|
| has_ai_feature | boolean | Yes | Any AI feature? (chatbot, content generation, recommendations, ranking/scoring, predictions, automated decisions) |
| eu_exposure | boolean | Yes | Available to people in the EU, or outputs used in the EU? Company location is irrelevant. |
| prohibited_practice | boolean | Yes | An Article 5 banned practice? (social scoring, harmful manipulation, exploiting vulnerabilities, untargeted face scraping, real-time remote biometric ID in public, emotion recognition at work/school, biometric categorisation by sensitive traits) |
| annex_iii_high_risk | boolean | Yes | An Annex III high-risk purpose? (biometric ID, critical infrastructure safety, education/exam scoring, hiring/worker management, access to essential services or creditworthiness, law enforcement, migration/border, justice) |
| user_facing_or_generative | boolean | Yes | Interacts directly with people (chatbot) or generates/alters content (text, image, audio, video, deepfakes)? |
| provides_own_gpai_model | boolean | Yes | Does the user TRAIN or PROVIDE their own general-purpose model? Using someone else's model via API is false. |
| system_description | string | No | Optional short free-text description of the AI system. |
Details
From the project READMEdisclos-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 — 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):
{
"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
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 © 2026 Gatis Ozols / Disclos. Original work, free to use, copy, modify and share.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.