Sovereign AI Act MCP
Classify any AI system under the EU AI Act: risk tier + binding Articles, verbatim from the law.
我该使用它吗
质量与安全性
发现（2）
- LOWTool 'lookup_article' description lacks action verb在 lookup_article 中
- LOWTool 'get_compliance_deadlines' description lacks action verb在 get_compliance_deadlines 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"sovereign-ai-act-mcp": {
"command": "npx",
"args": [
"sovereign-ai-act-mcp"
]
}
}
}可运行的软件包
1.4.0stdio远程端点
https://www.regulatoryai.eu/mcpstreamable-http它能做什么
工具清单
工具（5）
⚪classify_ai_system(description, language)
Classify an AI system under the EU AI Act (Regulation (EU) 2024/1689): risk tier (prohibited/high_risk/limited/minimal) + Annex III category + binding Articles, grounded verbatim in the law. Use whenever asked if an AI system is high-risk/prohibited or what obligations apply.
输入模式
{
"type": "object",
"properties": {
"description": {
"type": "string",
"description": "Plain-language description of the AI system."
},
"language": {
"type": "string",
"default": "en"
}
},
"required": [
"description"
]
}⚪lookup_article(number, language)
Verbatim text of an original EU AI Act Article (1–113) or inserted Article 4a, 60a or 75a–75d.
输入模式
{
"type": "object",
"properties": {
"number": {
"oneOf": [
{
"type": "integer",
"minimum": 1,
"maximum": 113
},
{
"type": "string",
"enum": [
"4a",
"60a",
"75a",
"75b",
"75c",
"75d"
]
}
]
},
"language": {
"type": "string",
"default": "en"
}
},
"required": [
"number"
]
}🟢search_eu_ai_act(query, language)
Full-text search across the EU AI Act corpus (Articles, Recitals, Annexes).
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"language": {
"type": "string",
"default": "en"
}
},
"required": [
"query"
]
}🟢get_compliance_deadlines
Canonical EU AI Act application dates (post Digital-Omnibus) + fine tiers.
输入模式
{
"type": "object",
"properties": {}
}🟢review_feature(input, language)
EU AI Act CO-PILOT review for builders: pass a feature, spec or behaviour you are about to ship and get a ship/caution/stop signal (OK / TRANSPARENCY / REVIEW REQUIRED / STOP), the binding Articles, the obligations that apply, red flags and concrete next steps — grounded verbatim in Regulation (EU) 2024/1689. Use proactively while designing or coding an AI feature, before it ships.
输入模式
{
"type": "object",
"properties": {
"input": {
"type": "string",
"description": "The AI feature, spec or behaviour you are about to build/ship."
},
"language": {
"type": "string",
"default": "en"
}
},
"required": [
"input"
]
}社区
证据