Trusteed Agentic Commerce

get_trust_receipt

Read-onlyIdempotent

Retrieve the signed trust receipt for a checkout. A receipt records the complete_checkout call; read order_placed before telling anyone a purchase happened. Returns the receipt id, the JWS signature and how to verify it. Issuance is asynchronous: right after complete_checkout this may answer status: "pending" with a retry delay. pending with code receipt_pending means the purchase completed and the receipt is on its way; checkout_in_progress means the complete_checkout call is still running. Only the credential that made the purchase can read its receipt. A receipt attests that the call happened, not that money moved: read settlement (it is not_attested unless the payment rail confirmed it). PREFER THE CART CARD: if the purchase was completed on an interactive card, it already fetches and shows this receipt itself right after the order — calling this tool yourself right after is usually redundant and opens a new card in the transcript. Call it yourself only when there is no interactive card, or the buyer asks for the receipt later in a new turn. Checkout guide: read the MCP resource trusteed://guides/checkout.

Input Schema

Name	Required	Description
`order_id`	No	The order id of a completed purchase, when you have the order but not the checkout session. Provide this or checkout_session_id.
`agent_key`	No	Sandbox credential from `create_sandbox_key`. Use this when your client cannot set an `Authorization: Bearer` header.
`checkout_session_id`	No	The checkout session id returned by create_cart and echoed by complete_checkout. Provide this or order_id.

Output Schema

Name	Required	Description	Default
`jws`	No
`code`	No
`docs`	No
`status`	Yes
`call_id`	No
`message`	No
`order_id`	No
`issued_at`	No
`dimensions`	No
`receipt_id`	No
`verify_url`	No
`verify_with`	No
`order_placed`	No
`checkout_status`	No
`does_not_attest`	No
`signature_status`	No
`retry_after_seconds`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 25, 2026

changedInput schema / properties / checkout_session_id / description

Previous value: -"The checkout session id returned by create_cart and echoed by complete_checkout."New value: +"The checkout session id returned by create_cart and echoed by complete_checkout. Provide this or order_id."

addedInput schema / properties / order_id

Added value: +{
+  "description": "The order id of a completed purchase, when you have the order but not the checkout session. Provide this or checkout_session_id.",
+  "type": "string"
+}

removedInput schema / required

Removed value: -[
-  "checkout_session_id"
-]

Changed1 schema field changedSep 28, 2026
- addedOutput schema / properties / verify_url
```
Added value: +{
+  "type": "string"
+}
```

Changed2 schema fields changedSep 26, 2026

addedOutput schema / properties / dimensions

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "chain_coverage": {
+      "additionalProperties": true,
+      "properties": {
+        "checkpoint_day": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "covered_through_seq": {
+          "anyOf": [
+            {
+              "type": "integer"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "receipt_seq": {
+          "anyOf": [
+            {
+              "type": "integer"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "status": {
+          "enum": [
+            "covered",
+            "not_covered",
+            "unknown"
+          ],
+          "type": "string"
+        }
+      },
+      "required": [
+        "status",
+        "receipt_seq",
+        "covered_through_seq",
+        "checkpoint_day"
+      ],
+      "type": "object"
+    },
+    "evidence_present": {
+      "enum": [
+        "present",
+        "absent",
+        "unknown"
+      ],
+      "type": "string"
+    },
+    "evidence_verified": {
+      "enum": [
+        "verified",
+        "not_verified",
+        "not_applicable"
+      ],
+      "type": "string"
+    },
+    "issuer_signed": {
+      "enum": [
+        "verified",
+        "present_unverified",
+        "absent",
+        "rejected"
+      ],
+      "type": "string"
+    },
+    "revocation": {
+      "additionalProperties": true,
+      "properties": {
+        "checked_at": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "freshness_seconds": {
+          "anyOf": [
+            {
+              "minimum": 0,
+              "type": "integer"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "status": {
+          "enum": [
+            "not_revoked",
+            "revoked",
+            "unknown"
+          ],
+          "type": "string"
+        },
+        "status_list_url": {
+          "type": [
+            "string",
+            "null"
+          ]
+        }
+      },
+      "required": [
+        "status",
+        "checked_at",
+        "freshness_seconds",
+        "status_list_url"
+      ],
+      "type": "object"
+    },
+    "settlement": {
+      "additionalProperties": true,
+      "properties": {
+        "rail_evidence_ref": {
+          "minLength": 1,
+          "type": "string"
+        },
+        "status": {
+          "enum": [
+            "settled",
+            "not_attested"
+          ],
+          "type": "string"
+        }
+      },
+      "required": [
+        "status"
+      ],
+      "type": "object"
+    },
+    "version": {
+      "const": "1.0",
+      "type": "string"
+    }
+  },
+  "required": [
+    "version",
+    "issuer_signed",
+    "evidence_present",
+    "evidence_verified",
+    "chain_coverage",
+    "revocation",
+    "settlement"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / does_not_attest

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

Changed2 schema fields changedSep 24, 2026
- addedOutput schema / properties / checkout_status
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / properties / order_placed
```
Added value: +{
+  "type": "boolean"
+}
```

Changed2 schema fields changedSep 22, 2026

addedInput schema / properties / agent_key

Added value: +{
+  "description": "Sandbox credential from `create_sandbox_key`. Use this when your client cannot set an `Authorization: Bearer` header.",
+  "type": "string"
+}

removedInput schema / properties / payment_mandate

Removed value: -{
-  "anyOf": [
-    {
-      "additionalProperties": {},
-      "type": "object"
-    },
-    {
-      "type": "string"
-    }
-  ],
-  "description": "Payment mandate with `mandate_id`, `max_amount_cents` (integer, minor units), `currency` (3 letters, must match the cart's), `exp` (expiry as an INTEGER of Unix seconds — not an ISO 8601 date string), `sub` (your agent id) and `aud` (the store slug this mandate is for, e.g. the slug in the URL you are calling — not a domain). Use this when your client cannot set an `X-Payment-Mandate` header."
-}

AddedSep 22, 2026

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered structurally. The description goes well beyond them, disclosing asynchronous issuance, the pending/receipt_pending/checkout_in_progress states, the credential scoping constraint, and the attestation-vs-settlement distinction. The only deduction is for not clarifying the pagination or response shape, though an output schema exists to cover that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then layered with state semantics and routing guidance. It is a single dense paragraph, and nearly every clause carries operational weight, but it runs long enough that the receipt-state rules and the 'prefer the cart card' rule compete for attention.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read tool with full annotation coverage and an output schema, this covers everything an agent needs: what it returns, async states and retry, error codes, auth scoping, and when calling it is redundant. A checkout guide resource is also referenced for deeper context. Nothing material is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the schema explains both order_id and checkout_session_id as alternatives, plus the agent_key fallback. The description adds nothing beyond this about parameter semantics itself. It also doesn't clarify that providing both ids or neither is acceptable, though required parameters are zero.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: "Retrieve the signed trust receipt for a checkout." It also defines what a receipt is and its relation to complete_checkout, which clearly separates it from checkout-state tools. It does not explicitly distinguish itself from the sibling verify_trust_receipt, leaving that boundary to be inferred from "how to verify it".

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-not guidance: "PREFER THE CART CARD... calling this tool yourself right after is usually redundant and opens a new card in the transcript." It then names the exact conditions under which an agent should call it instead (no interactive card, or a later turn), which is about as decisive as routing guidance gets.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Trusteed Agentic Commerce tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?