W-B. PaymentReceipt-to-mandate verification + Human-Not-Present autonomy gate (ART-62) -> mandate-chain re-validation (art-01) -> receipt aggregation (cry-05). Verifies an autonomous AP2 payment after the fact: valid receipt, intact mandate chain, in-policy autonomy.
verify_ap2_payment_receipt{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "verify_ap2_payment_receipt",
"arguments": {}
},
"id": 1
}
validate_ap2_mandate_chain{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "validate_ap2_mandate_chain",
"arguments": {}
},
"id": 1
}
aggregate_execution_receipts{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "aggregate_execution_receipts",
"arguments": {}
},
"id": 1
}
Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this whole workflow on the server and check one field that answers a real question.
Question: After an agent payment executes, what is the one session receipt root we can hand our auditor?
Run the AINumbers MCP tool `run_chain` with {"chain":"agent-economy-payment-receipt"} and read `cry-05-agent-action-audit-trail-aggregator.session_receipt_root`.
Re-run with `inputs` for `cry-05-agent-action-audit-trail-aggregator`, reusing the values that result echoed, with `artifacts` changed so one executed payment receipt joins the evidence. Compare the same field.
Verify: call `verify_execution_hash` (https://mcp.ainumbers.co/mcp) with `claimed_hash` set to `composite_execution_hash` and the full `composite_artifact`.
Ledger, for a human re-check: https://ledger.ainumbers.co/
PII rule: send synthetic or anonymised inputs only. The MCP server runs these kernels and logs no payloads.
Chain page: https://ainumbers.co/chaingraph/chains/agent-economy-payment-receipt.html