genpark-value-at-risk-cvar-expected-shortfall-skill

⚡ Overview & Architectural Significance

genpark-value-at-risk-cvar-expected-shortfall-skill delivers zero-dependency quantitative finance, option Greeks calculation, Monte Carlo stochastic simulations, and fixed-income analytics engineered strictly using Python 3.9+ standard library.

🌟 Key Architectural Capabilities

• Zero External Dependencies: Operates exclusively via pure Python (math, random, json). Zero NumPy/SciPy/QuantLib build dependencies.

• Enterprise Financial Invariants: Implements formal Black-Scholes-Merton analytic differentials, Geometric Brownian Motion stochastic walks, Historical & Parametric VaR/CVaR, Macaulay/Modified duration & convexity, and Nelson-Siegel yield curve parameterizations.

• Native Anthropic MCP Protocol: Compliant with standard JSON-RPC 2.0 stdio MCP specifications for Claude Desktop, Cursor, and Windsurf.

Related MCP server: genpark-black-scholes-merton-greeks-engine-skill

🏗️ Architectural Topology & State Machine

flowchart TD
    MarketData["Market Feed: Spot, Vol, Rates, Cash Flows"] --> RiskRouter["Quantitative Financial Router"]
    RiskRouter --> BSMEngine["Black-Scholes-Merton Greeks Engine"]
    RiskRouter --> MonteCarlo["Monte Carlo GBM Simulation Engine"]
    RiskRouter --> VaREngine["Value-at-Risk & Expected Shortfall"]
    RiskRouter --> BondEngine["Bond Duration & Convexity Evaluator"]
    RiskRouter --> YieldCurve["Nelson-Siegel Yield Curve Interpolator"]
    BSMEngine --> PortfolioSynthesis["Autonomous Risk Report & Hedging Strategy"]
    MonteCarlo --> PortfolioSynthesis
    VaREngine --> PortfolioSynthesis
    BondEngine --> PortfolioSynthesis
    YieldCurve --> PortfolioSynthesis

🚀 Quickstart & Standalone Execution

Local Python Client Usage

from client import RiskEngineVaRCVaR

# Initialize engine
engine = RiskEngineVaRCVaR()

# Execute self-testing benchmark suite
result = engine.benchmark_var_cvar_analysis()
print("Execution Result:", result)

🔌 One-Click MCP Integration (Claude Desktop / Cursor)

Add to your claude_desktop_config.json or cursor.json:

{
  "mcpServers": {
    "genpark-value-at-risk-cvar-expected-shortfall-skill": {
      "command": "python",
      "args": ["-u", "/path/to/genpark-value-at-risk-cvar-expected-shortfall-skill/mcp_server.py"]
    }
  }
}

📦 Smithery.ai & PyPI Deployment

This skill contains pre-configured smithery.yaml and pyproject.toml manifests. Install directly via pip:

pip install git+https://github.com/alphaparkinc/genpark-value-at-risk-cvar-expected-shortfall-skill.git