Recomputes a CCP's sequential default-waterfall loss allocation for a caller-declared defaulting-member loss, then checks whether the recomputed allocation stays within the CCP's Cover-2 default fund sizing or breaches it.
recompute_ccp_default_waterfall{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "recompute_ccp_default_waterfall",
"arguments": {}
},
"id": 1
}
size_ccp_default_fund_cover2{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "size_ccp_default_fund_cover2",
"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: A clearing member defaults owing far more than its posted margin. Does the loss stay inside the waterfall?
Run the AINumbers MCP tool `run_chain` with {"chain":"chain-ccp-default-waterfall"} and read `art-529-ccp-default-waterfall-recompute.loss_fully_absorbed`.
Re-run with `inputs` for `art-529-ccp-default-waterfall-recompute`, reusing the values that result echoed, with `loss_amount_minor_units` changed so loss_amount_minor_units is 600000000000, past every absorbable stage. 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/chain-ccp-default-waterfall.html