HPSILab - Quant Finance MCP Server¶

What It Is¶

HPSILab is an institutional-grade quantitative finance MCP server. It gives AI agents access to options analytics (Black-Scholes, Greeks), implied volatility surfaces, Monte Carlo simulations, AI market signals, and strategy backtesting. Uses Qiskit for quantum machine learning and includes regime detection.

Key differentiator from Hermes Plant: HPSILab targets the full quant stack (options, volatility, Monte Carlo, quantum ML) while Hermes Plant focuses on deterministic computation with crypto payment rails.

Tools Available¶

Tool Name	Description
`analyze_stock`	Comprehensive stock analysis with fundamentals and technical indicators
`get_iv_radar`	Implied volatility surface visualization and skew analysis
`get_option_pressure`	Options flow analysis - call/put volume, open interest, unusual activity
`get_monte_carlo`	Monte Carlo path generation, scenario analysis, VaR calculation
`get_ai_prediction`	AI-driven price predictions with confidence intervals
`get_equity_curves`	Strategy backtesting with transaction costs, slippage, benchmark comparison
`generate_stock_images`	Generate annotated stock charts with technical indicators
`generate_stock_research_report`	Full research report with fundamentals, technicals, and risk metrics
`get_pretrade_risk_scan`	Pre-trade risk assessment: margin, exposure, concentration limits

Quick Start¶

# Option 1: Remote endpoint (recommended - no local install)
hermes mcp add hpsilab --url https://hpsilab.com/mcp

# Option 2: Via PyPI (local install)
pip install hpsilab-mcp

# Option 3: From GitHub
git clone https://github.com/haiyunsky/hpsilab-quant-finance-mcp.git
cd hpsilab-quant-finance-mcp
pip install .
cp env.example .env
# edit .env and set HPSILAB_API_KEY=***

# Run the MCP server
hpsilab-quant-finance-mcp

# Add local install to Hermes
hermes mcp add hpsilab --command "hpsilab-quant-finance-mcp"

Business Use Cases¶

Options Trading: Price options, compute Greeks, and visualize volatility surfaces before executing trades
Risk Management: Run Monte Carlo VaR simulations across portfolios, stress-test for tail events
Quant Research: Backtest trading strategies with realistic transaction costs and slippage
Regime Detection: Automatically classify market regimes (trending, mean-reverting, high-vol) for strategy selection

Comparison: Finance MCP Landscape (July 2026)¶

Server	Focus	Best For
HPSILab	Full quant stack	Options traders, quant researchers, risk managers
Hermes Plant	Deterministic finance + crypto payments	Trustless financial computation, pay-per-call models
SentiSense	Market sentiment	Sentiment-driven investors, analyst consensus tracking
mcp-tradier	Real-time market data	Real-time quotes, streaming data
mcp-eodhd	Historical data	Backtesting, fundamental analysis
Kalshi MCP	Prediction markets	Event-driven trading, political forecasting

Limitations¶

Requires HPSILab account/API access
Quantum ML features are experimental (Qiskit dependency adds complexity)
Monte Carlo simulations are compute-intensive - not suitable for real-time trading
New server - models and signals unvalidated in production