Categories › Business & Finance › Legal & compliance documents
AI agent policy decisions: ALLOW, DENY, APPROVE, ESCALATE. 192 jurisdictions, signed evidence.
Remote server: your requests and data go to structureclerk.ca. Claude Code: claude mcp add --transport http structureclerk https://structureclerk.ca/api/mcp-http · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
compliance_check — Analyze regulatory obligations for a company based on jurisdiction, size and sector. Returns applicable frameworks, risk level and priority jurisdiction_map — Get applicable regulatory frameworks for a jurisdiction. Without a jurisdiction parameter, returns all 192 jurisdictions.compliance_roadmap — Generate a phased compliance action plan with cost estimates adapted to SME budgets.algorithmic_compliance_assessment — Assess algorithmic compliance maturity for AI systems. Returns applicable frameworks (EU AI Act, Law 25, AIDA/C-27, ISO 42001, NIST AI RMF),authority_decide — Deterministic, rule-based advisory decision (no LLM) on whether an AI agent may execute an action: ALLOW, APPROVE (human approval required),Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.