eu-ai-act-mcp
This MCP server provides structured intelligence and compliance tooling for the EU AI Act (Regulation (EU) 2024/1689), enabling LLMs and agents to reason accurately about AI regulation. You can:
Classify AI systems by risk level (prohibited, high-risk, limited, minimal) using free-text descriptions or structured signals (domain, biometric flags, synthetic content, etc.), returning matched signals, confidence level, relevant articles, and follow-up questions.
Check implementation deadlines with days remaining, a next-milestone shortcut, and Digital Omnibus details (e.g., high-risk Annex III obligations deferred to 2 December 2027).
Get compliance obligations for providers or deployers by risk level (high-risk, limited, minimal, GPAI), including Art. 53/55 GPAI obligations and the universal AI literacy requirement under Art. 4.
Answer EU AI Act questions from a curated FAQ of 24 entries covering classification, deadlines, roles, governance, documentation, penalties, GPAI systemic risk, FRIA, transparency, and sector-specific guidance.
Calculate penalties under Art. 99 for prohibited practices, high-risk violations, GPAI infringements, or false information, with SME/startup protection (Art. 99(6)).
Retrieve article summaries and stable EUR-Lex URLs for key articles (Art. 3–113) for grounded citations.
Assess GPAI systemic risk against the 10²⁵ FLOPs threshold (Art. 51(2)), returning Art. 53 baseline obligations, Art. 55 systemic-risk obligations, and Art. 52 notification duties.
Evaluate the Art. 6(3) exception for Annex III high-risk systems, including the profiling block, documentation requirement (Art. 6(4)), and registration duty (Art. 49(2)).
Generate Annex IV technical documentation checklists covering all nine items required under Art. 11, optionally as a markdown checklist, with SME-simplified notes.
Access structured resources: full Annex III high-risk categories, Annex IV documentation items, implementation timeline, and risk-level overviews.
Use guided prompts for system classification, compliance checklists, penalty risk assessment, and grounded article citation.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@eu-ai-act-mcpClassify my AI recruitment tool under the EU AI Act"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
EU AI Act MCP Server
An open-source Model Context Protocol (MCP) server that gives LLMs structured intelligence about the EU AI Act (Regulation (EU) 2024/1689, as amended by the Digital Omnibus, Regulation (EU) 2026/1744).
Built by Lexbeam Software - an agentic AI implementation boutique for regulated workflows.
What's new in 1.4.5
Version 1.4.5 is the npm follow-up to the 1.4.4 correctness release. It includes the complete 1.4.4 audit fixes and removes em dashes from documentation and served prose without changing legal rules, schemas, or tool behavior.
Twenty correctness fixes from a three-artifact audit with cross-model validation (details in CHANGELOG): honest FAQ answers with
matched_question, a reachableminimalclassification reconciled against the description text, a scoped Annex III(1)(a) verification exclusion, GPAI abstention instead of false negatives, penalty input guards plus the Art. 99(6a) SMC rule, and an article corpus current with the amended act including the new Art. 4a.All citation links point at the consolidated text (CELEX 02024R1689-20260727).
A pinned legal corpus (
law/) and two new gates: a 66-check claim matrix against the corpus and a 48-check post-serialization schema gate. The suite is date- and timezone-stable through 2031.
Full release history: CHANGELOG.md.
Related MCP server: ai-economy-infrastructure
Quick Start
npx (no install)
npx -y @lexbeam-software/eu-ai-act-mcpClaude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"eu-ai-act": {
"command": "npx",
"args": ["-y", "@lexbeam-software/eu-ai-act-mcp"]
}
}
}Smithery
npx -y @smithery/cli@latest mcp add lexbeam-software/eu-ai-actDirect MCP endpoint: https://mcp.lexbeam.com/mcp (health check at /health). Open, no auth required.
The Smithery-hosted endpoint https://eu-ai-act--lexbeam-software.run.tools requires Smithery authentication and returns 401 without it.
From source
git clone https://github.com/lexbeam-software/eu-ai-act-mcp.git
cd eu-ai-act-mcp
npm install
npm run build
npm start # stdio transport
npm run start:http # streamable HTTP (for Smithery/Railway)Tools
Tool | Description |
| Classify an AI system's risk level (prohibited / high-risk / limited / minimal) from free text or structured signals. Returns matched signals, missing signals, and follow-up questions. |
| Implementation milestones with days remaining, |
| Specific compliance obligations by role (provider/deployer) and risk level, including GPAI (Art. 51-56) and universal AI literacy (Art. 4). |
| Keyword FAQ search (lexical matching with stopword filtering, tie handling and abstention) across 24 curated EU AI Act questions; echoes your question and names the matched entry. |
| Calculate maximum fines by violation type, turnover, SME status (Art. 99(6)) and SMC status (Art. 99(6a), tiers 99(4)-(5) only), with a comparative non-SME vs SME block. |
| Retrieve an operational summary and EUR-Lex URL for a specific article. Covers 28 curated articles between Art. 3 and Art. 113 (including the new Art. 4a), not the full act. |
| Check whether a GPAI model crosses the 10²⁵ FLOPs threshold and return Art. 53 + Art. 55 obligations plus the Art. 52 notification duty. |
| Walk through the Art. 6(3) "no significant risk" exception with explicit profiling block and Art. 6(4) / Art. 49(2) reminders. |
| Return all nine Annex IV technical-documentation items, optionally as a markdown checklist. |
Resources
URI | Description |
| Key implementation milestones of the EU AI Act. |
| Overview of the four risk categories. |
| Full Annex III high-risk AI categories (1-8) with descriptions, examples, and article references. |
| Full Annex IV technical-documentation items (1-9). |
| The Digital Omnibus on AI (Regulation (EU) 2026/1744) as enacted: amended dates, deltas, and source status per item. |
Prompts
classify-my-system- guided classification usingeuaiact_classify_systemwith signal inferencecompliance-checklist- risk-level + role obligations checklist, including Annex IV for high-riskpenalty-risk-assessment- penalty calculation with SME comparativeground-citation- retrieve article text + EUR-Lex URL for grounded citations
Knowledge Base
Curated, structured data covering:
8 Annex III high-risk categories with keyword matching and examples
10 prohibited AI practices: Art. 5(1)(a)-(h), plus (ba) and (bb) applying from 2 December 2026
Art. 6(3) exception conditions with the profiling block rule
Art. 50 transparency triggers (chatbots, deepfakes, emotion recognition, machine-readable marking)
8 implementation milestones with dynamic days-remaining calculation
Digital Omnibus (enacted) status and impact assessment
Provider obligations (13 for high-risk, 8 for GPAI including Art. 53 + Art. 55)
Deployer obligations (9 for high-risk)
Limited-risk transparency obligations (4 under Art. 50)
Universal AI literacy (Art. 4)
Penalty framework with SME protection logic (Art. 99)
24 FAQ entries with article references and Lexbeam knowledge-base links
28 article summaries with EUR-Lex URLs to the consolidated text
Annex IV (9 documentation items) (new in 1.1.0)
Load-bearing dates, thresholds, amounts and exceptions are checked on every build by a claim matrix (test-claims.mjs) against a pinned, hash-verified copy of the consolidated act (law/). Coverage is the matrix, not a blanket claim.
Regulatory Accuracy
This server tracks the current state of the EU AI Act (Regulation 2024/1689) as amended by the Digital Omnibus on AI, Regulation (EU) 2026/1744, published in the Official Journal on 24 July 2026 and in force from 27 July 2026. The amended application dates are served as operative law. Article-level wording was verified against the enacted OJ text on 26 and 27 July 2026, delta by delta against the 43 numbered amendments in Article 1 of the amending act. No Omnibus delta was left unresolved in that reconciliation. The Art. 49 registration duty for self-assessed not-high-risk systems, previously carried as unresolved, SURVIVES: the enacted act does not amend Art. 49 and deletes only Annex VIII Section B points 7 and 9.
Operative dates as amended:
2 Feb 2025 - Prohibited practices (Art. 5) + AI literacy (Art. 4), in effect
2 Aug 2025 - GPAI model obligations, in effect
2 Aug 2026 - Art. 50 transparency, and Commission GPAI enforcement powers and fines. Not deferred
2 Dec 2026 - The two new Art. 5 prohibitions (non-consensual intimate material, CSAM), and the Art. 111(4) deadline for synthetic-content systems already on the market to meet Art. 50(2)
2 Aug 2027 - Legacy GPAI models (Art. 111(3)), unchanged
2 Dec 2027 - High-risk Annex III obligations. Deferred from 2 Aug 2026
2 Aug 2028 - High-risk Annex I regulated products. Deferred from 2 Aug 2027
Development
npm install
npm run build # typescript -> dist/
node test.mjs # full suite incl. ten agent journeys
node test-claims.mjs # claim matrix: pinned law corpus vs served facts
node test-schemas.mjs # post-serialization output-schema gate
npm run dev # stdio dev server
npm run dev:http # HTTP dev serverDisclaimer
This MCP server is a structured information tool that returns references to and summaries of Regulation (EU) 2024/1689. It is not Rechtsberatung im Sinne des § 2 RDG and does not constitute legal advice in any jurisdiction. It cannot replace consultation with a qualified Rechtsanwalt or equivalent licensed professional. Use of this tool does not establish a lawyer-client relationship. For implementation support, visit lexbeam.com/kontakt.
License
MIT. See LICENSE. Regulation text summarised in src/knowledge/articles.ts and src/knowledge/annex-iv.ts is derived from Regulation (EU) 2024/1689 as amended; EUR-Lex content is reused under the conditions of Commission Decision 2011/833/EU (preserve attribution, do not distort the meaning of the source).
About Lexbeam
Lexbeam Software builds agentic AI for compliance, legal operations, internal audit, and risk workflows.
Give us one ugly, regulation-heavy workflow. We'll turn it into a working AI system fast.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityAmaintenanceEU AI Act Compliance - MCP server providing AI-powered tools and automation by MEOK AI Labs119MIT
- AlicenseAqualityCmaintenanceAn MCP server for AI economy infrastructure with built-in EU AI Act compliance, supporting risk management, transparency, and bias detection.10MIT
- AlicenseAqualityDmaintenanceMCP server for EU AI Act compliance, providing risk classification of AI features and Article 50 transparency notices.21Apache 2.0
- Alicense-qualityAmaintenanceAn MCP server that provides tools for deterministic EU AI Act risk classification and documentation generation, enabling human-in-the-loop AI system assessments inside Claude Code.1MIT
Related MCP Connectors
Connect AI to millions of laws and court cases with the Lawstronaut MCP.
MCP server giving Claude AI access to 22+ NYC public-record databases for real estate due diligence
MCP server connecting AI agents to non-custodial staking data across 130+ networks.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/lexbeam-software/eu-ai-act-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server