CrashTestYourStrategy

AIエージェント向けポートフォリオおよび取引戦略のストレス診断：ヘッジ破綻検出を伴うマルチアセットストレス、毎日の事前登録レジーム見通し、デフレート・シャープレシオによるバックテスト整合性チェック。リモートのストリーミングHTTP対応、無料ティア、認証不要。

GitHub

ドキュメント

CrashTestYourStrategy — MCP Server

Remote MCP server for portfolio & trading-strategy stress diagnostics. Free tier — no key, no signup. Descriptive, never advisory.

https://mcp.crashtestyourstrategy.ai/mcp

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.

Quick start

Claude Code:

claude mcp add --transport http ctys https://mcp.crashtestyourstrategy.ai/mcp

Generic MCP client config (streamable HTTP):

{
  "mcpServers": {
    "ctys": {
      "type": "streamable-http",
      "url": "https://mcp.crashtestyourstrategy.ai/mcp"
    }
  }
}

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.

What it does

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.

Response contract

Every response is a versioned envelope (ctys-agent-v1 family) carrying:

grounding_summary — a risk-focused factual statement of the omitted tail
revision_required — a gate-capable signal (never a directive)
methodological_limitations — required disclosure of what the diagnostic does NOT establish
data_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.

Scope & compliance

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).