The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Crashtestyourstrategy listing page.
Remote MCP server for portfolio & trading-strategy stress diagnostics. Free tier — no key, no signup. Descriptive, never advisory.
Listed in the official MCP registry as
io.github.fnobbe/crashtestyourstrategy. This repository is the public server card —
the service itself is closed-source; everything an agent (or a reviewer) needs to
verify behaviour is linked below.
Claude Code:
Generic MCP client config (streamable HTTP):
claude.ai: Settings → Connectors → Add custom connector with the URL above.
The free tier is rate-limited per IP (30 req/min). No account, no key.
An open diagnostics layer that confronts a proposed portfolio or trading strategy with the failure modes an optimistic backtest ignores — hedge breaks (the 2022 stock-bond case), sequence-of-returns risk, regime blind spots, deflated Sharpe.
Free tier (16 tools)
| Group | Tools |
|---|---|
| Portfolio | portfolio_stress_test (multi-asset stress across baseline / risk-off / rate-shock regimes, hedge-break detection, full drawdown distribution) · portfolio_compare · factor_decomposition · ips_gate (hard gate vs an Investment Policy Statement, breach probability not median path) · long_horizon_stress (multi-year savings/withdrawal plans, ruin probabilities) |
| Strategy | run_stress_test · challenge_strategy · backtest_integrity (deflated Sharpe + which crisis regimes the backtest window missed) |
| Regimes | regime_outlook (model-conditional BULL/SIDEWAYS/BEAR/CRISIS probabilities at 5/21 trading days — preregistered, out-of-sample validated, refreshed daily) · market_regime_map (18-category cross-asset map) · describe_regime · find_similar_regime |
| Record & catalog | list_investment_theses · get_investment_thesis · get_dossier (citable audit trail of prior calls) · submit_feedback |
Full tier (token via contact):
tier2_stress_test (stress any ticker with auto-calibration + realism gate),
build_portfolio, portfolio_frontier.
Every response is a versioned envelope (ctys-agent-v1 family) carrying:
grounding_summary — a risk-focused factual statement of the omitted tailrevision_required — a gate-capable signal (never a directive)methodological_limitations — required disclosure of what the diagnostic does NOT establishdata_through / data_staleness_days — self-reported data freshness (EOD, refreshed daily)validation:// resources expose the realism trust layer: 18 measured stylized facts
per asset vs historical reference bands — the falsifiability surface. Recompute
locally; trust by independent reproduction.
Model-based scenario simulation. Descriptive, never advisory: no suitability, timing, or ranking claim is made or implied — the agent decides what "suitable" means. Out-of-sample limits are disclosed, not hidden (e.g. the GFC hedge-behaviour test failed and ships as a documented limitation).
Maintainer: @fnobbe · Operator contact: https://crashtestyourstrategy.com/contact