Trust Gate

Post-quantum, tamper-evident receipts for agent actions. Ed25519 + ML-DSA-65, offline verify.

Sollte ich dies verwenden

Qualität und Sicherheit

A
Qualität der Beschreibung
85%
Vollständigkeit des Schemas
74%
Qualität der Benennung
100%
Risiko der Vergiftung
100%
Übereinstimmung der Berechtigungen
100%
Einhaltung des Protokolls
100%

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

Kontextkosten

~748Tokens (Tool-Definitionen)
~1.7 KBTypische Antwortgröße
Mittlere Auswirkung auf die Aufmerksamkeit (0.58% 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": {
    "trust-gate-mcp": {
      "url": "https://trust-gate-mcp.onrender.com/mcp"
    }
  }
}

Remote-Endpunkte

https://trust-gate-mcp.onrender.com/mcpstreamable-http

Was es kann

Tool-Inventar

Tools (4)

🟢 Nur lesen🟡 Schreiben🔴 Löschen⚪ Unbekannt
🟡mint_receipt_for_record_change(record_id, object_type, field, old_value, new_value, ...)

Mint a post-quantum receipt for one CRM record change. Old/new values are carried as SHA-256 hashes. Works with any CRM (Relaticle, hosted CRMs, custom).

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "record_id": {
      "title": "Record Id",
      "type": "string"
    },
    "object_type": {
      "title": "Object Type",
      "type": "string"
    },
    "field": {
      "title": "Field",
      "type": "string"
    },
    "old_value": {
      "title": "Old Value",
      "type": "string"
    },
    "new_value": {
      "title": "New Value",
      "type": "string"
    },
    "changed_by_agent": {
      "title": "Changed By Agent",
      "type": "string"
    },
    "tenant": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Tenant"
    },
    "policy": {
      "default": "per-decision CRM change evidence",
      "title": "Policy",
      "type": "string"
    }
  },
  "required": [
    "record_id",
    "object_type",
    "field",
    "old_value",
    "new_value",
    "changed_by_agent"
  ],
  "title": "mint_receipt_for_record_changeArguments"
}

Ausgabe-Schema

{
  "type": "object",
  "properties": {
    "result": {
      "additionalProperties": true,
      "title": "Result",
      "type": "object"
    }
  },
  "required": [
    "result"
  ],
  "title": "mint_receipt_for_record_changeOutput"
}
🟢audit_my_agent_inventory(inventory, notes)

Rank a CALLER-PROVIDED list of MCP tools by worst-regret if they act, with a signed receipt. Cannot auto-discover the inventory -- MCP does not allow that; the caller must pass it in.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "inventory": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Inventory",
      "type": "array"
    },
    "notes": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Notes"
    }
  },
  "required": [
    "inventory"
  ],
  "title": "audit_my_agent_inventoryArguments"
}

Ausgabe-Schema

{
  "type": "object",
  "properties": {
    "result": {
      "additionalProperties": true,
      "title": "Result",
      "type": "object"
    }
  },
  "required": [
    "result"
  ],
  "title": "audit_my_agent_inventoryOutput"
}
🟡mint_action_receipt(agent_id, operation, target, policy, inputs, ...)

Mint a post-quantum receipt for an arbitrary consequential agent action.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "agent_id": {
      "title": "Agent Id",
      "type": "string"
    },
    "operation": {
      "title": "Operation",
      "type": "string"
    },
    "target": {
      "title": "Target",
      "type": "string"
    },
    "policy": {
      "default": "agent action evidence",
      "title": "Policy",
      "type": "string"
    },
    "inputs": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Inputs"
    },
    "decision": {
      "default": "ACTION_GOVERNED",
      "title": "Decision",
      "type": "string"
    }
  },
  "required": [
    "agent_id",
    "operation",
    "target"
  ],
  "title": "mint_action_receiptArguments"
}

Ausgabe-Schema

{
  "type": "object",
  "properties": {
    "result": {
      "additionalProperties": true,
      "title": "Result",
      "type": "object"
    }
  },
  "required": [
    "result"
  ],
  "title": "mint_action_receiptOutput"
}
⚪verify_receipt(receipt, require_pq)

Verify a Trust Gate receipt from the certificate alone (offline). require_pq=True (default via OAO_REQUIRE_PQ) FAILS if the ML-DSA-65 or SLH-DSA legs are missing -- defends against signature-stripping downgrade attacks.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "receipt": {
      "additionalProperties": true,
      "title": "Receipt",
      "type": "object"
    },
    "require_pq": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Require Pq"
    }
  },
  "required": [
    "receipt"
  ],
  "title": "verify_receiptArguments"
}

Ausgabe-Schema

{
  "type": "object",
  "properties": {
    "result": {
      "additionalProperties": true,
      "title": "Result",
      "type": "object"
    }
  },
  "required": [
    "result"
  ],
  "title": "verify_receiptOutput"
}

Community

Diesen Server bewerten

Nachweis

Aktuelle Beobachtungen

verifiziertVersion nicht aufgezeichnet4 Tools
verifiziertVersion nicht aufgezeichnet4 Tools
verifiziertVersion nicht aufgezeichnet4 Tools