READ

acf.regulation.article

Fetch the verified text of a regulatory article (AI Act, GDPR, DORA, NIS2, ISO 42001) and its operational translation into ACF®: activated principles, cards that operationalise it, implementation note and date of application.

iNote

READ tools return signed corpus content with no inference layer. The text field summarises the article, with its official reference in source: for a regulatory filing, always cite the official text (OJEU/CELEX, ISO…).

When to use

Use this tool when a regulator, auditor or board references a specific article and you have to return (a) the verified text and (b) its ACF® operational reading. Examples: “AI Act Art. 9, how do you cover it?”, “GDPR Art. 35, does your DPIA include the agent?”, “DORA Art. 28, critical third parties?”. The tool returns the text and the bridge to your cards in one shot.

The output has a pedagogical and scoping intent: it explains which ACF® principles the article activates and which toolkit cards operationalise it. This is the “translator” angle between hard law and operations, it does not replace legal advice.

Input parameters

Three fields. regulation is a strict enum; article is the bare number, without “Art.”.

regulation"ai-act" | "gdpr" | "dora" | "nis2" | "iso-42001"required

Canonical regulation identifier. Five guides published; any other value is rejected.

articlestring (1-20)required

Article or clause number, without prefix. Covered articles: AI Act 9, 10, 12, 13, 14; GDPR 5, 22, 25, 30, 35; DORA 5, 6, 11, 17, 28; NIS2 20, 21, 23; ISO 42001 6, 8, 9 and A (Annex A).

locale"en" | "fr"default: "en"

Language of the title, text and operational note.

Output schema

A JSON object: the article, its summary, its official reference and its ACF® translation.

regulationstring

Identifier of the requested regulation.

articlestring

Number of the requested article.

titlestring

Article heading (“Human oversight” for AI Act Art. 14).

textstring

Summary of the article, with a pointer to the official text.

mapping{ principles: string[], fiches: string[], operational_note: string }

ACF® translation: activated principles (P1 to P4), toolkit cards that operationalise it and implementation note.

sourcestring

Official reference (regulation, directive or standard, and article).

applicable_datestring (ISO date)

Date of application of the article when known.

Example call

The agent prepares a regulator-question answer on AI Act Art. 14 (human oversight):

regulation-article.tstypescript

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";

const transport = new StdioClientTransport({
  command: "npx",
  args: ["-y", "acf-mcp"],
});
const client = new Client({ name: "demo", version: "1.0" }, {});
await client.connect(transport);

const result = await client.callTool({
  name: "acf.regulation.article",
  arguments: {
    regulation: "ai-act",
    article: "14",
    locale: "en",
  },
});

console.log(JSON.stringify(result.content, null, 2));

Response

response.jsonjson

{
  "regulation": "ai-act",
  "article": "14",
  "title": "Human oversight (high-risk AI)",
  "text": "High-risk AI systems shall be designed so they can be effectively overseen by natural persons during use, including through stop mechanisms. See Regulation (EU) 2024/1689, Article 14.",
  "mapping": {
    "principles": [
      "P3"
    ],
    "fiches": [
      "ACF-07",
      "ACF-P6",
      "ACF-P7"
    ],
    "operational_note": "ACF operationalises Art. 14 via P3 (ultimate human control), ACF-07 (kill switch), ACF-P6 (escalation thresholds), ACF-P7 (human-takeover drills)."
  },
  "source": "Regulation (EU) 2024/1689, Article 14",
  "applicable_date": "2027-12-02"
}

Common errors

“Article ai-act Art. 15 not found. Available articles for ai-act: 9, 10, 12, 13, 14.”: the article is not covered, the message lists the covered ones. Pass the bare number, without “Art.”.
Unknown regulation: any value outside the five identifiers fails parameter validation; the JSON-RPC error names the regulation field.

acf.fiche.lookup: fetch the cards listed in mapping.fiches.
acf.search: when the exact article is unknown, run a text search to locate it.
acf.map-ai-act-obligations: for the AI Act, get the exhaustive set of articles applicable to a high-risk agent, not just one.