Open-source harness and MCP dataset for options trading with AI agents
Open-source harness and MCP dataset for options trading with AI agents
This repository provides an open-source agent workflow harness for the GammaRips MCP curated options dataset, which each trading day filters roughly 3,500 optionable US stocks down to a cohort of contracts passing liquidity and quantitative gates (mid price ≥ $1.00, open interest ≥ 500, delta 0.22–0.48, DTE 10–45, RV/IV ≥ 0.85). Agents pull the daily cohort via MCP endpoints (OAuth Pro, Bearer API key, or a free no-key preview), layer their own catalyst research, and build trade plans using historical MFE/MAE excursion data, with a three-step workflow and skills for trade, review, and coach. The repo includes agent instructions, trading doctrine, operations docs, local eval logs, and validators, and states it is a financial data vendor offering educational and research material configured for paper trading by default, not investment advice.
Source: Hacker News AI · github.com