W-F. Agent identity & authorization attestation (art-04) -> agent-traffic acceptance policy (art-21) -> service metering/pricing (ART-63). Onboards an agent service into a micropayment marketplace with a metered, policy-gated listing.
check_agent_attestation{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "check_agent_attestation",
"arguments": {}
},
"id": 1
}
build_agent_traffic_policy{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "build_agent_traffic_policy",
"arguments": {}
},
"id": 1
}
model_agent_service_metering{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "model_agent_service_metering",
"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 marketplace is drafting its acceptance limits for agent traffic. Does a five-thousand-dollar single-transaction cap still read as sound policy?
Run the AINumbers MCP tool `run_chain` with {"chain":"agent-economy-marketplace"} and read `art-21-agent-traffic-acceptance-policy-builder.verdict`.
Re-run with `inputs` for `art-21-agent-traffic-acceptance-policy-builder`, reusing the values that result echoed, with `max_single_val_usd` set to 5000. 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-marketplace.html