MCP App Store
by KeenEthics
Regit PRIIPs icon

Regit PRIIPs MCP Server for ChatGPT

By NICOLAS JOËL HUBERT KOENIG

Overview

Regit PRIIPs calculates risk, performance-scenario, and cost figures from supplied product data with an authorized PRIIPs engine. It compares published and fresh KID figures for numeric Article 15 review triggers and returns structured results, coverage, and traces.

How to connect

  1. ChatGPT: Open the Regit PRIIPs listing in the ChatGPT app directory and choose Connect. ChatGPT listing Regit PRIIPs exposes 27 tools here.

Tools

cat3_curve_market_states

ChatGPT
Generates a content-addressed Category-3 principal-component interest-rate/curve market-state batch (Annex II point 23) for a stated purpose (market risk, performance, or stress). Use to produce the simulated curve paths a Category-3 valuation or scenario request consumes; it does not value a PRIIP.

cat3_spot_market_states

ChatGPT
Generates aligned Category-3 spot/level market-state paths, sampling one historical row per simulated step across all spot observables. Use to produce the simulated spot paths a Category-3 valuation or scenario request consumes; it does not value a PRIIP.

costs_breakdown

ChatGPT
Aggregates itemised and statutory-derived cost amounts into the Article 5(3) / Annex VI 'Composition of costs' categories (one-off; recurring split into transaction/other; incidental) and the point-61 total. Use for any PRIIP's cost disclosure once itemised charges are known.

costs_riy

ChatGPT
Computes the per-holding-period Reduction-in-Yield (RIY = i - r) summary cost indicator from two internal rates of return over a cashflow series, per Annex VI points 62 / 70-72 / 90 and Article 5(1)/(2). Use for the 'Costs over time' percentage figure of any PRIIP.

costs_tables

ChatGPT
Composes costs_breakdown and costs_riy outputs into the Annex VII 'Costs over time' and 'Composition of costs' tables (Article 5(2)/(3)), adding non-blocking economic-plausibility warnings. Use as the final costs-presentation step for any PRIIP.

crm_class_assignment

ChatGPT
Maps an adjusted credit-quality step (CQS 0-6) to a credit-risk-measure (CRM) class 1-6 via the Annex II Part 2 point-45 table, applying mitigating / escalating factors, or short-circuits when the market-risk-measure class is 7 (point 30). Use once a PRIIP's CQS is known.

crm_credit_quality_step

ChatGPT
Derives a PRIIP's adjusted credit-quality step (CQS 0-6) from obligor credit assessments (direct, ECAI-mapped, or no-assessment default), guarantor substitution, and combination/maturity adjustments, per Annex II Part 2 points 32-43. Use for any PRIIP bearing credit risk.

crm_monitoring

ChatGPT
Re-attributes the CRM class the instant a fresh assessment differs from the current one, per Annex II Part 3 point 54 (no smoothing or majority vote, unlike MRM monitoring). Use during ongoing KID review of a PRIIP's credit risk.

kid_review_comparison

ChatGPT
Evaluates the Article 15(2)(b)/(c) numeric KID-review predicates: whether an MRM / CRM change forces a summary-risk-indicator class move, and whether the moderate- scenario return shifted by more than five percentage points. Use during the periodic (at least every 12 months) or trigger-based KID review of any PRIIP.

mop_ranges

ChatGPT
Aggregates the Article 12(1)(a) / Annex III point-5 SRI class range (min/max) and the Article 13 / Annex VII per-cell cost ranges across a multi-option product's offered underlying investment options. Use for the generic-KID route of a MOP under Articles 10-14.

mrm_cat1

ChatGPT
Computes the Category-1 market-risk-measure class via the trivial point-8 lookup (class 7, or 6 for the point-4(c) exception) -- no VaR/VEV simulation. Use for PRIIPs with no market-risk-measure volatility, per Annex II Part 1 point 4.

mrm_cat2

ChatGPT
Computes the Category-2 market risk measure: VaR and VEV from the observed return history via moments and Cornish-Fisher, per Annex II Part 1 points 5 / 9-14. Use for non-leveraged (or constant-multiple) PRIIPs with sufficient price history.

mrm_cat3

ChatGPT
Routes Category-3 market risk to either complete governed valuations (formula 7 over simulated PRIIP values) or the exact Annex II point-24 unconditional- protection shortcut. Use for PRIIPs whose value depends on complex or path-dependent underlyings requiring simulation.

mrm_cat4

ChatGPT
Computes the Category-4 market risk measure: routes each component (Category-2, Category-3, protected, or manufacturer-governed unobserved) to its own VEV engine and combines them by proportional weight, per Annex II Part 1 points 25-29. Use for PRIIPs with components not fully observed in the market.

mrm_class_assignment

ChatGPT
Maps a VaR-equivalent volatility (VEV) to a market-risk-measure class 1-7 via the Annex II Part 1 point-2 threshold table, applying the points 15/18 monthly-only +1 adjustment. Use for Category 2, 3, or 4 PRIIPs; Category 1 is rejected (use mrm_cat1 instead).

mrm_monitoring

ChatGPT
Re-attributes the MRM class using a strict-majority vote over per-reference-point MRM-class observations across the preceding four months, per Annex II Part 3 points 53/55, with an explicit policy/strategy-change predicate. Use during ongoing KID review of a PRIIP's market risk.

past_performance

ChatGPT
Derives a PRIIP's per-year past-performance return series (NAV basis, income reinvested) and an aligned benchmark series, per Annex VIII points 2 / 4 / 11-14. Use for UCITS/AIF/unit-linked products required to show a past-performance chart.

performance_scenario_presentation

ChatGPT
Applies the atomic Annex IV point-42/44/45/46 monetary and percentage presentation rules (receipt summation, monetary rounding, ordinary and derivative returns) over already-selected scenario outcomes. Use as the final presentation step after any performance-scenario engine; it does not select scenarios or price payoffs.

scenarios_autocall_presentation

ChatGPT
Applies exact-time cash-flow, annualisation, and blank-cell presentation arithmetic over four already-selected complete autocall path outcomes (Annex IV/V; current Q&A XII.1). Use for autocallable products after path selection; it does not model the payoff or barrier.

scenarios_cat1

ChatGPT
Routes Category-1 performance scenarios to one of three treatments (Annex IV points 29-31): the Category-3 engine for point-4(a) or non-traded point-4(b) PRIIPs, governed best estimates for point 31, or a pay-off-structure graph for exchange-traded futures/options. Use for Category-1 PRIIPs.

scenarios_cat2

ChatGPT
Computes the four Category-2 performance scenarios (favourable / moderate / unfavourable / stress) at the recommended holding period from historical net returns via rolling sub-intervals and Cornish-Fisher stress, per Annex IV points 5-20. Use for non-leveraged PRIIPs with sufficient price history.

scenarios_cat3

ChatGPT
Finalizes Category-3 performance scenarios from complete governed observed-drift and stress PRIIP valuation batches, selecting percentile outcomes per Annex IV points 21-27. Use for complex/path-dependent PRIIPs after market-state simulation.

scenarios_cat3_intermediate

ChatGPT
Finalizes Category-3 performance scenarios at an intermediate (non-RHP) holding period from complete governed valuations, or applies the point-38 RHP-only election. Use for complex PRIIPs that must show shorter-horizon scenarios.

scenarios_cat4

ChatGPT
Blends per-component performance-scenario values (Category-2/3 market components plus manufacturer-supplied unobserved-factor components) into a weighted-average favourable/moderate/unfavourable/stress set, per Annex IV point 28. Use for Category-4 PRIIPs with components not fully observed in the market.

scenarios_intermediate_periods

ChatGPT
Computes the four Category-2 scenarios at the Annex IV points 32-34 intermediate holding-period set (end of year 1, half-RHP, RHP) by re-running the Category-2 historical method at each shorter sub-interval length. Use for Category-2 PRIIPs whose recommended holding period exceeds one year.

scenarios_point31

ChatGPT
Computes complete manufacturer-supplied Annex IV point-31 best-estimate scenarios at every displayed horizon, for Category-1 point-4(c) PRIIPs or the Category-2 Q&A VI.15 governed-estimate route. Use when the standard historical/simulated method cannot apply.

sri_compose

ChatGPT
Composes the final summary risk indicator (SRI 1-7) from the MRM (1-7) and CRM (1-6) classes via the Annex II Part 3/4 point-52 grid, applies the optional point-52a manufacturer increase, and classifies liquidity risk (points 56-58). Use as the final SRI step for any PRIIP.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/regit-priips"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/regit-priips)