加载中…
AI agent policy decisions: ALLOW, DENY, APPROVE, ESCALATE. 192 jurisdictions, signed evidence.
StructureClerk 是 ChatHome Skills 收录的 MCP 条目，来源为 Official MCP Registry，质量分 93/100。 作为 Model Context Protocol 服务器，它向 Claude、Cursor、Copilot 等兼容 MCP 的 LLM 客户端暴露可直接调用的工具，让 agent 的能力超出模型内置范围。 该条目由 ChatHome Skills 的每日抓取从官方 registry 和 GitHub 发现查询中收录，每次运行都会重新核验仓库事实、新鲜度信号和安装元数据。 质量分综合了官方 registry 收录情况、可用安装命令、许可证完整性、仓库活跃度和 GitHub star 趋势，完整算法说明见来源页。安装命令已列于上方，可直接复制使用。 在将 StructureClerk 加入生产 agent 工作流前，请核对上方的最近更新日期和仓库状态——下方事实快照是最近一次抓取的时点值。
mcp add ca.structureclerk/mcp https://structureclerk.ca/api/mcp-http运行此命令前，请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-08-19T17:55:12.73734Z",
"publishedAt": "2026-08-19T17:55:12.73734Z",
"statusChangedAt": "2026-08-19T17:55:12.73734Z"
}
},
"server": {
"name": "ca.structureclerk/mcp",
"_meta": {
"io.modelcontextprotocol.registry/publisher-provided": {
"tools": [
{
"name": "authority_decide",
"metered": true,
"description": "Deterministic, rule-based advisory decision on whether an AI agent may execute an action: ALLOW, APPROVE, DENY or ESCALATE, with framework-level citations and signed evidence."
},
{
"name": "compliance_check",
"metered": false,
"description": "Analyze regulatory obligations for a company based on jurisdiction, size and sector."
},
{
"name": "jurisdiction_map",
"metered": false,
"description": "Get applicable regulatory frameworks for a jurisdiction, or list all 192."
},
{
"name": "compliance_roadmap",
"metered": false,
"description": "Generate a phased compliance action plan with cost estimates."
},
{
"name": "algorithmic_compliance_assessment",
"metered": false,
"description": "Assess algorithmic compliance maturity against EU AI Act, Law 25, ISO 42001 and NIST AI RMF."
}
],
"schema": "https://structureclerk.ca/spec/authority-decision-v0.1.schema.json",
"license": {
"note": "The decision contract under /spec is MIT-licensed. The service implementing it is proprietary.",
"specification": "MIT"
},
"pricing": "https://structureclerk.ca/api/v1/pricing",
"tagline": "Policy decisions for AI agents: ALLOW, DENY, APPROVE, ESCALATE across 192 jurisdictions. Signed evidence included.",
"keywords": [
"AI agent authorization",
"agent governance",
"policy engine",
"compliance",
"GDPR",
"Law 25",
"EU AI Act",
"signed evidence"
],
"publisher": {
"url": "https://structureclerk.ca",
"name": "TechVibes Inc.",
"contact": "info@structureclerk.ca"
},
"categories": [
"compliance",
"governance",
"legal",
"security"
],
"publicKeys": "https://structureclerk.ca/.well-known/structureclerk-authority.json",
"documentation": "https://structureclerk.ca/docs",
"specification": "https://structureclerk.ca/spec/openapi.json",
"authentication": {
"note": "Public. A daily free allowance applies; beyond it, authenticate with 'Authorization: Bearer sk_sc_...' to spend prepaid credits.",
"required": false
},
"longDescription": "StructureClerk answers what an AI agent is allowed to do, before it acts. It compiles regulatory mapping — data protection across 192 jurisdictions, AI governance in 18, cybersecurity in 5 — into deterministic, rule-based decisions: ALLOW, APPROVE (human approval required), DENY (reserved for humans) or ESCALATE (below the confidence threshold). Every decision cites the applicable frameworks at framework level, and ships with an Ed25519 signature and a position in an append-only chained log, so any third party can verify it without trusting the issuer. Decisions are advisory: StructureClerk decides, your infrastructure enforces.",
"protocolVersion": "2025-03-26"
}
},
"title": "StructureClerk",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://structureclerk.ca/api/mcp-http",
"type": "streamable-http"
}
],
"version": "2.0.0",
"websiteUrl": "https://structureclerk.ca/authority",
"description": "AI agent policy decisions: ALLOW, DENY, APPROVE, ESCALATE. 192 jurisdictions, signed evidence."
}
}