Skip to content
TotalFinance

risk · wire operation

Value-at-Risk & Conditional VaR

Estimate Value-at-Risk (VaR) and Conditional VaR / expected shortfall from a return series. Methods: historical (empirical quantile, default), parametric (Gaussian, optional Cornish-Fisher for skew/kurtosis), or monteCarlo. Both are positive loss magnitudes at the given `confidence`; the horizon scales by √-time. The applied confidence/method/horizon ride `assumptions` (with the resolved seed/samples for monteCarlo) and warnings ride `diagnostics`.

totalfinance.risk.value_at_risk
MCP tool name
totalfinance_risk_value_at_risk
Pack / profiles
risk / default, full, portfolio
Default discovery
Included in the default tool set
Required capabilities
None
Effects / authorization
none / none
Cost / cancellation
small / Do not assume inline interruption
Handle-eligible inputs
None
Idempotency
not-applicable

Input schema

FieldTypeMeaning
returnsRequirednumber[]Periodic returns as decimals (e.g. 0.01 = +1%)
confidenceOptionalnumberConfidence level in (0, 1); default 0.95
methodOptional"historical" | "parametric" | "monteCarlo"Estimation method; default historical
horizonPeriodsOptionalnumberHolding-period horizon in periods; scales by √-time; default 1
cornishFisherOptionalbooleanParametric only: Cornish-Fisher adjustment for skew/excess-kurtosis
samplesOptionalintegerMonte-Carlo only: number of simulated paths; default 10000, capped at 1,000,000 (compute is bounded BEFORE the work starts, not just by the deadline).
seedOptionalintegerMonte-Carlo only: PRNG seed; default 0
Complete JSON Schema

Loading…

Output schema

FieldTypeMeaning
valueRequiredobject—
assumptionsRequiredobjectconfidence, method, horizonPeriods, cornishFisher, conventionsVersion (+ seed/samples when method is monteCarlo)
diagnosticsRequiredobjectmethod + warnings
Complete JSON Schema

Loading…