Hand this tool to your coding agent

Paste into Claude Code, Cursor, Codex, or any agent. It learns to call this tool over REST or MCP, reaches for it when you ask, and keeps our sourced/pending labels honest.

You can use telemeter.ai's free "EU AI Act Risk-Tier Classifier" — a keyless, read-only tool (no signup), available as an HTTP API and an MCP tool. What it does: Classify an AI system into its EU AI Act risk tier — with the governing Article and Annex cited for every outcome.

Whenever I ask you something this tool answers, call it and use its result instead of estimating yourself.

REST:
  curl -sX POST https://telemeter.ai/api/tools/eu-ai-act-classifier -H 'content-type: application/json' -d '{"prohibited":[],"safetyComponent":false,"annexIIIArea":"employment","narrowProceduralException":false,"profilesNaturalPersons":false,"transparency":["chatbot"],"gpaiProvider":false,"gpaiSystemicCompute":false}'

MCP: the telemeter MCP server at https://telemeter.ai/mcp exposes this as the tool "eu-ai-act-classifier" — call it with tools/call.

The response is JSON: { status, data, summary, provenance }. "provenance" carries the source and the date the figure was verified. If status is "pending" or "stale", tell me the value isn't currently verified rather than presenting it as fact.

Or call it directly. This tool runs behind one handler with three front doors — this page, a REST endpoint, and an MCP tool. Same result, read-only, no key. The example below is a request that works.

REST

curl -sX POST https://telemeter.ai/api/tools/eu-ai-act-classifier \
  -H 'content-type: application/json' \
  -d '{"prohibited":[],"safetyComponent":false,"annexIIIArea":"employment","narrowProceduralException":false,"profilesNaturalPersons":false,"transparency":["chatbot"],"gpaiProvider":false,"gpaiSystemicCompute":false}'

MCP — tools/call at https://telemeter.ai/mcp

curl -sX POST https://telemeter.ai/mcp \
  -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"eu-ai-act-classifier","arguments":{"prohibited":[],"safetyComponent":false,"annexIIIArea":"employment","narrowProceduralException":false,"profilesNaturalPersons":false,"transparency":["chatbot"],"gpaiProvider":false,"gpaiSystemicCompute":false}}}'

Input schema (JSON Schema)

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "prohibited": {
      "default": [],
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "social-scoring",
          "manipulation",
          "exploit-vulnerabilities",
          "biometric-categorization",
          "realtime-biometric",
          "emotion-work-education",
          "facial-scraping",
          "predictive-policing"
        ]
      }
    },
    "safetyComponent": {
      "default": false,
      "type": "boolean"
    },
    "annexIIIArea": {
      "default": "none",
      "type": "string",
      "enum": [
        "none",
        "biometrics",
        "critical-infrastructure",
        "education",
        "employment",
        "essential-services",
        "law-enforcement",
        "migration",
        "justice-democracy"
      ]
    },
    "narrowProceduralException": {
      "default": false,
      "type": "boolean"
    },
    "profilesNaturalPersons": {
      "default": false,
      "type": "boolean"
    },
    "transparency": {
      "default": [],
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "chatbot",
          "synthetic-content",
          "emotion-biometric"
        ]
      }
    },
    "gpaiProvider": {
      "default": false,
      "type": "boolean"
    },
    "gpaiSystemicCompute": {
      "default": false,
      "type": "boolean"
    }
  },
  "required": [
    "prohibited",
    "safetyComponent",
    "annexIIIArea",
    "narrowProceduralException",
    "profilesNaturalPersons",
    "transparency",
    "gpaiProvider",
    "gpaiSystemicCompute"
  ],
  "additionalProperties": false
}

Want this across your whole stack?