StructureClerk
AI agent policy decisions: ALLOW, DENY, APPROVE, ESCALATE. 192 jurisdictions, signed evidence.
使うべきか
品質と安全性
検出事項（1）
- LOWTool 'algorithmic_compliance_assessment' name length outside 3-30 rangealgorithmic_compliance_assessment 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"mcp": {
"url": "https://structureclerk.ca/api/mcp-http"
}
}
}リモートエンドポイント
https://structureclerk.ca/api/mcp-httpstreamable-httpできること
ツール一覧
ツール（5）
🟢compliance_check(jurisdiction, company_size, sector, processes_personal_data, uses_ai)
Analyze regulatory obligations for a company based on jurisdiction, size and sector. Returns applicable frameworks, risk level and priority actions.
入力スキーマ
{
"type": "object",
"properties": {
"jurisdiction": {
"type": "string",
"description": "ISO code (e.g. QC, FR, DE, US)"
},
"company_size": {
"type": "string",
"description": "e.g. 1-10, 11-50, 51-250, 250+"
},
"sector": {
"type": "string",
"description": "e.g. tech, health, finance, retail"
},
"processes_personal_data": {
"type": "boolean"
},
"uses_ai": {
"type": "boolean"
}
},
"required": [
"jurisdiction"
]
}🟢jurisdiction_map(jurisdiction)
Get applicable regulatory frameworks for a jurisdiction. Without a jurisdiction parameter, returns all 192 jurisdictions.
入力スキーマ
{
"type": "object",
"properties": {
"jurisdiction": {
"type": "string",
"description": "ISO code (e.g. QC, FR, DE). Omit for full list."
}
}
}⚪compliance_roadmap(jurisdiction, company_size, sector, budget, timeline_months)
Generate a phased compliance action plan with cost estimates adapted to SME budgets.
入力スキーマ
{
"type": "object",
"properties": {
"jurisdiction": {
"type": "string",
"description": "ISO code (e.g. QC, FR, DE, US)"
},
"company_size": {
"type": "string",
"description": "e.g. 1-10, 11-50, 51-250, 250+"
},
"sector": {
"type": "string"
},
"budget": {
"type": "string",
"description": "low, medium or high"
},
"timeline_months": {
"type": "number",
"description": "Number of months for the plan"
}
},
"required": [
"jurisdiction"
]
}⚪algorithmic_compliance_assessment(jurisdiction, sector)
Assess algorithmic compliance maturity for AI systems. Returns applicable frameworks (EU AI Act, Law 25, AIDA/C-27, ISO 42001, NIST AI RMF), sector-specific obligations and assessment dimensions.
入力スキーマ
{
"type": "object",
"properties": {
"jurisdiction": {
"type": "string",
"description": "ISO code (e.g. QC, FR, DE, US, EU)"
},
"sector": {
"type": "string",
"description": "e.g. health, finance, hr, legal, tech, education, retail, manufacturing"
}
},
"required": [
"jurisdiction"
]
}⚪authority_decide(agent, action, context)
Deterministic, rule-based advisory decision (no LLM) on whether an AI agent may execute an action: ALLOW, APPROVE (human approval required), DENY (human-only decision) or ESCALATE (doubt threshold). Cites applicable frameworks per jurisdiction and sector, and returns an evidence record. Advisory only: StructureClerk decides, your infrastructure enforces.
入力スキーマ
{
"type": "object",
"properties": {
"agent": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Caller-assigned agent identifier"
},
"autonomy_level": {
"type": "integer",
"minimum": 1,
"maximum": 3,
"description": "1 supervised, 2 augmented, 3 autonomous"
}
},
"required": [
"id",
"autonomy_level"
]
},
"action": {
"type": "object",
"properties": {
"type": {
"type": "string",
"description": "Dotted action type, e.g. payment.execute, read.contract"
},
"amount": {
"type": "number"
},
"currency": {
"type": "string",
"description": "3-letter code, e.g. CAD"
},
"data_categories": {
"type": "array",
"items": {
"type": "string"
},
"description": "e.g. personal, health, biometric, minors, financial"
},
"irreversible": {
"type": "boolean"
}
},
"required": [
"type"
]
},
"context": {
"type": "object",
"properties": {
"jurisdictions": {
"type": "array",
"items": {
"type": "string"
},
"description": "ISO codes, e.g. QC, FR, EU"
},
"sector": {
"type": "string",
"description": "e.g. health, finance, public, insurance, tech"
}
},
"required": [
"jurisdictions",
"sector"
]
}
},
"required": [
"agent",
"action",
"context"
]
}コミュニティ
エビデンス