Trust Gate

Working · 2.4 s

io.github.CWNApps/trust-gate-mcpv0.2.0

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

Security

Source Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

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

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

audit_my_agent_inventory

Rank a CALLER-PROVIDED list of MCP tools by worst-regret if they act (a name-based heuristic that weights a name's first word most). Read-only: it mints no receipt. Cannot auto-discover the inventory -- MCP does not allow that; the caller must pass it in.

inventoryarray, required

notesstring

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Tools (7)

audit_my_agent_inventory

Argument	Type	Description
notes	any
inventory*	array

Input schema (JSON)

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

check_egress

Egress classification check. Scans a data sample for a finite list of sensitivity markers and classifies as NO_MARKERS_FOUND / INTERNAL / CONFIDENTIAL / RESTRICTED. RESTRICTED sets blocked=true; this tool cannot block anything itself, and NO_MARKERS_FOUND is not clearance to send. Returns classification, retention info, and a tamper-evident receipt.

Argument	Type	Description
provider*	string
data_sample*	string
destination*	string

Input schema (JSON)

{
  "type": "object",
  "title": "check_egressArguments",
  "required": [
    "destination",
    "data_sample",
    "provider"
  ],
  "properties": {
    "provider": {
      "type": "string",
      "title": "Provider"
    },
    "data_sample": {
      "type": "string",
      "title": "Data Sample"
    },
    "destination": {
      "type": "string",
      "title": "Destination"
    }
  }
}

gate_decision

Two-phase decision gate with a real verdict. PREVIEW returns ALLOW, DENY or ESCALATE with the risk tier and reasons, plus a preview_id, without acting. COMMIT re-evaluates the same inputs and mints a signed receipt for the verdict. Only ALLOW returns a GRANTED permit; DENY returns DENIED; ESCALATE returns WITHHELD_PENDING_HUMAN and a human must decide outside this tool. Applies only to actions the caller routes through it: it does not observe or block what an agent does. Verb-tier heuristic on the action name and resource, not a proof. Stateless. Optional attestation: triggered_by_type, triggered_by_source, decision_model.

Argument	Type	Description
phase	string
action*	string
context*	object
resource*	string
preview_id	any
decision_model	any
triggered_by_type	any
triggered_by_source	any

Input schema (JSON)

mint_action_receipt

Mint a signed receipt (Ed25519, plus ML-DSA-65 when the post-quantum backend is available) for an arbitrary consequential agent action. Optional attestation: triggered_by_type (human/agent/script), triggered_by_source (api/cli/cron), decision_model (the LLM model used). Attestation values are caller claims: allowlisted to safe characters, signed, not verified. Decisions that contain a gate verdict word are reserved for gate_decision.

Argument	Type	Description
inputs	any
policy	string
target*	string
agent_id*	string
decision	string
operation*	string
decision_model	any
triggered_by_type	any
triggered_by_source	any

Input schema (JSON)

mint_receipt_for_record_change

Mint a signed receipt (Ed25519, plus ML-DSA-65 when the post-quantum backend is available) for one CRM record change. Old/new values are carried as SHA-256 hashes. Works with any CRM (Relaticle, hosted CRMs, custom).

Argument	Type	Description
field*	string
policy	string
tenant	any
new_value*	string
old_value*	string
record_id*	string
object_type*	string
changed_by_agent*	string

Input schema (JSON)

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

run_exit_drill

Vendor exit readiness drill. Checks local signing key, local model access (Ollama). Returns step-by-step results and a tamper-evident receipt. Informational; it signs one receipt, which creates the signing key on a host that has none yet.

No arguments.

Input schema (JSON)

{
  "type": "object",
  "title": "run_exit_drillArguments",
  "properties": {}
}

verify_receipt

Verify a Trust Gate receipt from the certificate alone (offline). ok=true means unchanged since signing, signed, kid consistent with the embedded key, and (require_pq default on) at least one post-quantum leg verified; unsigned receipts fail. It does not prove who signed: pass expected_kid to pin the signer's Ed25519 key; a pin counts only when that key's own signature verifies (see signer_pinned). The post-quantum keys in a receipt are not covered by the kid.

Argument	Type	Description
receipt*	object
require_pq	any
expected_kid	any

Input schema (JSON)

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