W-A. Voucher-to-onchain batch reconciliation + settlement-risk window (ART-61) -> independent Merkle re-verification (cry-04) -> one Merkle-root settlement receipt (cry-05). The flagship Wave-14 runtime decision: did this batch of agent micro-payments settle correctly?
reconcile_x402_batch_settlement{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "reconcile_x402_batch_settlement",
"arguments": {}
},
"id": 1
}
verify_merkle_batch{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "verify_merkle_batch",
"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 the x402 batch closes, how many settled receipts does the evidence pack actually hold?
Run the AINumbers MCP tool `run_chain` with {"chain":"agent-economy-batch-settlement"} and read `cry-05-agent-action-audit-trail-aggregator.n_receipts`.
Re-run with `inputs` for `cry-05-agent-action-audit-trail-aggregator`, reusing the values that result echoed, with `artifacts` changed so one settled voucher receipt joins the batch. 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-batch-settlement.html