mcp-gateway

get_trust_receipt

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 it has not settled yet. Only the credential that made the purchase can read its receipt. 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: https://trusteed.xyz/.well-known/agent-checkout-guide.json.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`agent_key`	No	Sandbox credential from `create_sandbox_key`. Use this when your client cannot set an `Authorization: Bearer` header.
`checkout_session_id`	Yes	The checkout session id returned by create_cart and echoed by complete_checkout.

Output Schema

TableJSON 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.

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

A4.6/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so: asynchronous issuance, the `status: "pending"` response with a retry delay, the distinction between `receipt_pending` (purchase completed) and `checkout_in_progress` (not settled), and the authorization constraint that only the purchasing credential can read the receipt. This is exactly the behavioral context an agent needs before acting on a purchase.

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?

Long but front-loaded: purpose first, then the critical 'read order_placed before telling anyone a purchase happened' caution, then behavior, then routing. Nearly every sentence earns its place, though the density of status-code detail is close to the limit of what one paragraph should hold.

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 two-parameter read tool with an output schema already describing the return shape, the description covers everything else an agent needs: async timing, retry semantics, authorization scope, and the interactive-card preference. 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 coverage is 100%, so both parameters (agent_key, checkout_session_id) are already fully documented in the schema. The description adds no syntax or format detail beyond what the schema provides, so the baseline 3 applies.

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

Purpose5/5

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') and immediately distinguishes itself from the sibling complete_checkout by noting the receipt records that call. An agent can tell what this returns and how it differs from adjacent checkout tools.

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?

Explicitly states when to call and when NOT to: 'PREFER THE CART CARD... calling this tool yourself right after is usually redundant... Call it yourself only when there is no interactive card, or the buyer asks for the receipt later in a new turn.' That is a rare, precise routing rule with the alternative named.

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

All mcp-gateway 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?