Categories › Business & Finance › Market data, stocks & crypto
Backtests with costs, a held-out test that counts once, a score that counts every version tried.
Remote server: your requests and data go to quantwright.com. Claude Code: claude mcp add --transport http quantwright https://quantwright.com/api/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
describe_data — Start here to backtest a trading idea. This server holds the price history (US stocks and ETFs, FX, spot gold and silver, spot crypto; dailycreate_study — Opens a study, the named set of runs every backtest belongs to: call it once per question, before run_backtest. Can set a hold-out period, orun_backtest — Backtests a trading rule on this server's price history: one backtesting.py Strategy class, one symbol, one bar size, in a study. Use it to get_result — Reads a backtest result by its run_id (when run_backtest answered "running", call this until the run ends), or a study's runs by study_id (orun_held_out_test — The final out-of-sample check: runs a finished run's exact code once over its study's hold-out period. Call it at the end, on the run you wocompare_trades — Checks a trader's own trades against a run's rule, on the price history this server holds: for each trade, in their order, whether the rule Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.