Generic, jurisdiction-neutral segregation check: segregated custody assets against customer claims, per asset class and rolled up. FULLY_SEGREGATED at or above 1.0, UNDER_SEGREGATED below it, OVER_SEGREGATED above an optional configurable ceiling. A zero-claims line resolves a null ratio and NO_CLAIMS_OUTSTANDING, never a division artifact. Aggregate totals only, never a per-customer or per-wallet line item.
Aggregate totals by asset class and custody location type.
Aggregate totals by asset class. Leave a class absent from both lists out; leave claims empty for a class to see the zero-claims edge.
| Asset class | Segregated ($M) | Claims ($M) | Ratio | Status |
|---|
Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this exact tool, with this sample, and verify the artifact.
Run the AINumbers MCP tool `compute_custody_segregation_ratio`. Task: Compute a segregation ratio (segregated custody assets / customer claims) per asset class and overall, with FULLY_SEGREGATED / UNDER_SEGREGATED / OVER_SEGREGATED / NO_CLAIMS_OUTSTANDING status.
Call it with arguments: {"policy_parameters":{"segregated_assets":[{"asset_class":"cash","custody_location_type":"qualified_custodian_bank","amount_musd":60},{"asset_class":"securities","custody_location_type":"qualified_custodian_bank","amount_musd":30},{"asset_class":"BTC","custody_location_type":"cold_storage_multisig","amount_musd":25}],"customer_claims":[{"asset_class":"cash","amount_musd":50},{"asset_class":"securities","amount_musd":30},{"asset_class":"BTC","amount_musd":20}],"over_segregation_ceiling":null}}
Verify before trusting: call `verify_execution_hash` on mcp.ainumbers.co (https://mcp.ainumbers.co/mcp) with the parameter `claimed_hash` set to the returned `execution_hash`, passing the full artifact the run returned (the object containing `policy_parameters` + `output_payload` + `execution_hash`; equivalently `policy_parameters` + `output_payload` with `claimed_hash`), not the bare hash string.
Return the ledger link https://ledger.ainumbers.co/ so a human can re-verify without contacting us.
PII rule: All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only.
Open the tool with the sample prefilled: https://ainumbers.co/chaingraph/art-538-custody-segregation-ratio.html#p=v1.H4sIAAAAAAAA_wHbAST-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