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

Integration with CorpusIQ¶

CorpusIQ is the connector layer that lets AI assistants read the systems a business already runs on - accounting, payments, CRM, email, files and analytics - and answer with the source named. It is read-only by design: it retrieves data and never writes to, or acts in, a connected system, which is what makes it safe to point at live accounts.

This page is part of the CorpusIQ directory, the reference we maintain for the MCP server and agent-skill ecosystem. Run alongside CorpusIQ, a third-party server like this one can be combined with a company's own business data in a single answer.

See what CorpusIQ connects

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