Backtest any trading setup on the S&P 500 vs random days, and see which stocks matched today.
Scored across 4 tools
Each tool has a distinct role: rule_language is reference documentation, scan_today applies a custom rule to the latest close, test_setup backtests a rule historically, and what_happened_today reports fixed scans and market breadth. The only mild overlap is that scan_today and what_happened_today both surface today's matches, but custom vs fixed scans and the breadth summary make the boundary clear.
scan_today and test_setup follow a verb_noun pattern, but rule_language is a noun phrase and what_happened_today is a question-style name. The names are readable and memorable, yet they mix conventions rather than following one predictable pattern.
Four tools are well-scoped for a trading research server: documentation, a live scan, a backtest, and a market snapshot. Each earns its place and none feels redundant or missing for the core workflow.
The surface covers rule authoring guidance, daily scanning, historical validation, and a market overview, which is solid lifecycle coverage for setup research. Minor gaps remain, such as inspecting an individual stock's history or saving/reusing named rules, but agents can work around them.
How to write a rule for test_setup and scan_today: the available names, operators and examples.
Inputs: no named parameters. Returns: result
List the S&P 500 stocks that match a setup at the latest daily close (e.g. "what broke out today on volume").
rule: a formula in Trade Manager's language, e.g. "close > prev_high and volume > volume_avg * 1.5".
limit: max stocks to return (default 25). Stocks where the rule just turned true come first,
then by volume vs their 20-day average. Uses end-of-day data, not live prices.Inputs: rule (required), limit.
Backtest a trading setup on every S&P 500 stock since 2017 and compare it with random days.
rule: a formula in Trade Manager's language (see the server instructions), e.g. "rsi < 30".
horizon_days: how many trading days after the signal to check (1-60, default 20).
Returns how often the stock was higher after the signal vs random days on the same stocks
(same year, never the signal's own month) and vs the stock's all-days rate, split by period,
plus a plain verdict and recent examples. History, not a prediction.Inputs: rule (required), horizon_days.
What happened on the S&P 500 at the latest close: how many stocks rose and fell, how many sit 10%/20% below their 1-year high, and today's matches for fixed scans (5% drops with RSI under 30, breakouts on 2x volume, RSI above 80, 200-day dips in an uptrend, golden crosses, 5% drops), each with its record since 2017 vs random days and, where one exists, a link that opens that exact alert on trademanager.site.
Inputs: limit.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Test a plain-words trading rule on historical prices and compare the trades with SPY. Not advice.
Backtest US stock setups on 400K+ Trade-Ideas alerts since 2019. Your agent picks from 250+ filters, sees what happened on the day of every matching event, and simulates intraday entries and exits (win rate, profit factor, P&L per share). Also: ticker overviews, per-ticker gap history and today's premarket gappers. Pro adds a live market scanner and paper trading. Connect with OAuth or an API key; the free plan includes 50 requests a day.
Backtest S&P 500 stocks and ETFs on real prices, plus loan, savings, FIRE and retirement tools.
Backtest plain-English trading strategies on real market data: graded results, honesty flags.
Add one secure layer between your agents and this server.
