W-D. Metering + marketplace unit economics (ART-63) -> x402 settlement cost/finality (art-03) -> usage/billing anomaly monitoring (ml-03). Models the economics of an agent-service micropayment marketplace. Educational estimator.
model_agent_service_metering{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "model_agent_service_metering",
"arguments": {}
},
"id": 1
}
model_x402_settlement{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "model_x402_settlement",
"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 metering feed watches for billing anomalies. If the series carries six injected spikes, how many periods get flagged?
Run the AINumbers MCP tool `run_chain` with {"chain":"agent-economy-metering"} 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 `nAnomalies` set to 6. 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-metering.html