AI Act Radar
EU AI Act obligations and updates from ten official sources, incl. the national layer.
我該用這個嗎
品質與安全性
發現項目（1）
- LOWTool 'lookup_article' description lacks action verb在 lookup_article 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"ai-act-radar": {
"url": "https://mcp.aiactradar.com/mcp/v1"
}
}
}遠端端點
https://mcp.aiactradar.com/mcp/v1streamable-http它能做什麼
工具清單
工具（4）
🟢query_ai_act_updates(since, until, source_id, topics, severity_min, ...)
Query EU AI Act regulatory updates from primary sources. Returns structured events with titles, summaries, severity, topics and source URLs. Optionally filter by date range, source, topics, or severity. Use this when you need recent or historical regulatory changes affecting AI builders, GPAI providers, or deployers.
輸入結構描述
{
"type": "object",
"properties": {
"since": {
"type": "string",
"description": "ISO 8601 timestamp; only events published after this. Optional."
},
"until": {
"type": "string",
"description": "ISO 8601 timestamp; only events published before this. Optional."
},
"source_id": {
"type": "string",
"description": "One of: eurlex, aioffice, aiboard, codeofpractice, haveyoursay, cen, bnetza, bfdi, bsi, cnil, nl-algoritmeregister, oecdai. Optional."
},
"topics": {
"type": "array",
"items": {
"type": "string"
},
"description": "Topic taxonomy. e.g. [\"gpai\",\"transparency\",\"high-risk\"]. Optional."
},
"severity_min": {
"type": "string",
"enum": [
"info",
"low",
"medium",
"high",
"critical"
],
"description": "Minimum severity. Optional."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 200,
"default": 25
}
}
}🟢get_obligation_for_role(role, risk_category)
Look up the AI Act obligations for a specific role and AI-system risk category. Returns the relevant articles, recent guidance updates, and applicable templates. This is informational, not legal advice.
輸入結構描述
{
"type": "object",
"properties": {
"role": {
"type": "string",
"enum": [
"provider",
"deployer",
"distributor",
"importer",
"gpai-provider"
],
"description": "The AI Act role you operate as."
},
"risk_category": {
"type": "string",
"enum": [
"prohibited",
"high-risk",
"limited-risk",
"minimal-risk",
"gpai",
"gpai-systemic-risk"
],
"description": "The AI Act risk classification of the system you offer or use."
}
},
"required": [
"role",
"risk_category"
]
}⚪summarize_changes_since(since, topics, language)
Generate a structured digest of all AI Act regulatory changes since a given date, grouped by topic and severity. Useful for weekly compliance reviews or audit prep. Returns Markdown.
輸入結構描述
{
"type": "object",
"properties": {
"since": {
"type": "string",
"description": "ISO 8601 date; the digest covers everything from this date forward."
},
"topics": {
"type": "array",
"items": {
"type": "string"
},
"description": "Restrict digest to these topics. Optional."
},
"language": {
"type": "string",
"enum": [
"en",
"de"
],
"default": "en"
}
},
"required": [
"since"
]
}⚪lookup_article(article)
Look up a specific AI Act article (e.g. "Art. 53(1)(d)" or "Annex III") and return all related events from our pipeline plus the official EUR-Lex URL.
輸入結構描述
{
"type": "object",
"properties": {
"article": {
"type": "string",
"description": "Article identifier — e.g. \"Art. 53\", \"Art. 53(1)(d)\", \"Annex III\", \"Recital 60\"."
}
},
"required": [
"article"
]
}社群
證據