Apply an NGFS / Fit-for-55 scenario path to an exposure set -> stress-adjusted metrics (ART-76) -> audit receipt (cry-05). The bank/insurer climate-risk computation a supervisor re-verifies. Scenario paths are versioned reference data, not the suite financial-shock stress parameters.
apply_climate_scenario{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "apply_climate_scenario",
"arguments": {}
},
"id": 1
}
aggregate_execution_receipts{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "aggregate_execution_receipts",
"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 climate stress runs on the orderly NGFS path. What carbon price does the 2030 horizon assume?
Run the AINumbers MCP tool `run_chain` with {"chain":"climate-scenario"} and read `art-76-climate-scenario-applicator.carbon_price_assumption`.
Re-run with `inputs` for `art-76-climate-scenario-applicator`, reusing the values that result echoed, with `scenario` changed so the scenario family is NGFS-disorderly. 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/climate-scenario.html