StructureClerk

AI agent policy decisions: ALLOW, DENY, APPROVE, ESCALATE. 192 jurisdictions, signed evidence.

Sollte ich dies verwenden

Qualität und Sicherheit

A
Qualität der Beschreibung
100%
Vollständigkeit des Schemas
92%
Qualität der Benennung
76%
Risiko der Vergiftung
100%
Übereinstimmung der Berechtigungen
100%
Einhaltung des Protokolls
100%

Befunde (1)

  • LOWTool 'algorithmic_compliance_assessment' name length outside 3-30 rangein algorithmic_compliance_assessment

Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.

Kontextkosten

~819Tokens (Tool-Definitionen)
~1.3 KBTypische Antwortgröße
Mittlere Auswirkung auf die Aufmerksamkeit (0.64% von 128k Kontext)

Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.

Installieren

Installation mit einem Klick

Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:

{
  "mcpServers": {
    "mcp": {
      "url": "https://structureclerk.ca/api/mcp-http"
    }
  }
}

Remote-Endpunkte

https://structureclerk.ca/api/mcp-httpstreamable-http

Was es kann

Tool-Inventar

Tools (5)

🟢 Nur lesen🟡 Schreiben🔴 Löschen⚪ Unbekannt
🟢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.

Eingabe-Schema

{
  "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.

Eingabe-Schema

{
  "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.

Eingabe-Schema

{
  "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.

Eingabe-Schema

{
  "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.

Eingabe-Schema

{
  "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"
  ]
}

Community

Diesen Server bewerten

Nachweis

Aktuelle Beobachtungen

verifiziertVersion nicht aufgezeichnet5 Tools
verifiziertVersion nicht aufgezeichnet5 Tools