W-C. Cross-document consistency + Merkle provenance (ART-55) -> independent Merkle re-verification (cry-04) -> invoicing/volume anomaly monitoring (ml-03). Detects inconsistent or tampered trade-document sets.
verify_trade_document_set{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "verify_trade_document_set",
"arguments": {}
},
"id": 1
}
verify_merkle_batch{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "verify_merkle_batch",
"arguments": {}
},
"id": 1
}
detect_timeseries_anomalies{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "detect_timeseries_anomalies",
"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: Our trade doc set runs through a money-laundering red-flag screen. Which periods get flagged as outliers, and what does tightening the z threshold do to that count?
Run the AINumbers MCP tool `run_chain` with {"chain":"digital-trade-doc-integrity"} and read `ml-03-timeseries-anomaly-detector.anomalies_flagged`.
Re-run with `inputs` for `ml-03-timeseries-anomaly-detector`, reusing the values that result echoed, with `zThreshold` set to 1. 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/digital-trade-doc-integrity.html