Shipped: HPSILab — Quant Finance MCP Server
Check the risk before every trade: pre-trade risk scans, options pressure and Monte Carlo ranges for traders and AI agents, over MCP and REST.
Generic market feeds tell an AI agent what happened. HPSILab tells it what the risk looks like before it acts.
One pip install -U hpsilab-mcp gives Claude Code, Codex or any MCP client:
- Pre-Trade Check: a stock's risk vs the SPY benchmark, sizing checks, sector exposure and correlation with what you already hold
- Options structure: IV radar, gamma wall, call/put walls and max pain for the nearest expiry
- Monte Carlo: 10-day price range and odds of finishing higher
- Next-day probability with model agreement, plus backtested equity curves
- Grover Picks: quantum search for the best 1–3 stock portfolio in a watchlist, checked against the classical best
Coverage: US, Japan, Hong Kong, China A-shares and Singapore (options data for US stocks and ETFs).
Research only. HPSILab never executes trades.
Free: watch 3 stocks with daily risk alerts. Trader/Developer: $19/mo.
Agents
MCPFintechTrading
Comments2
Welcome to Lounge, Haiyun. Publishing every prediction and option level before the outcome and scoring misses is a rare kind of trust signal for a finance tool. Which metric on the accuracy page do agent builders ask about most, calibration of the Monte Carlo ranges or the next-day hit rate?
Thanks Ryan. It's still early, but what agent builders seem to need first isn't a hit rate, it's numbers they can size on and limits they can't talk around. That's where most of our work goes: Monte Carlo ranges for the next 10 days, options structure (IV regime, gamma and put/call walls) and a pre-trade check that compares a position with SPY and with what's already held. The direction model is one input among those, and we keep scoring it in public so its weight can be judged honestly: hpsilab.com/ — Haiyun
2 comments
Welcome to Lounge, Haiyun. Publishing every prediction and option level before the outcome and scoring misses is a rare kind of trust signal for a finance tool. Which metric on the accuracy page do agent builders ask about most, calibration of the Monte Carlo ranges or the next-day hit rate?
Thanks Ryan. It's still early, but what agent builders seem to need first isn't a hit rate, it's numbers they can size on and limits they can't talk around. That's where most of our work goes: Monte Carlo ranges for the next 10 days, options structure (IV regime, gamma and put/call walls) and a pre-trade check that compares a position with SPY and with what's already held. The direction model is one input among those, and we keep scoring it in public so its weight can be judged honestly: hpsilab.com/ — Haiyun