io.github.amitblecher/trade-manager is an MCP server published by io.github.amitblecher, hosted at amitblecher10--trade-manager-mcp-web.us-east.modal.run. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 4 tools, including test_setup, scan_today, rule_language, what_happened_today.
Backtest any trading setup on the S&P 500 vs random days, and see which stocks matched today.
2 connections through 4 shared values. Tap any node.
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.
| Parameter | Type | Description |
|---|---|---|
| rule * | string | |
| horizon_days | integer |
{
"name": "test_setup",
"description": "Backtest a trading setup on every S&P 500 stock since 2017 and compare it with random days.\n\n rule: a formula in Trade Manager's language (see the server instructions), e.g. \"rsi < 30\".\n horizon_days: how many trading days after the signal to check (1-60, default 20).\n Returns how often the stock was higher after the signal vs random days on the same stocks\n (same year, never the signal's own month) and vs the stock's all-days rate, split by period,\n plus a plain verdict and recent examples. History, not a prediction.",
"inputSchema": {
"type": "object",
"title": "test_setupArguments",
"required": [
"rule"
],
"properties": {
"rule": {
"type": "string",
"title": "Rule"
},
"horizon_days": {
"type": "integer",
"title": "Horizon Days",
"default": 20
}
}
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
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.
| Parameter | Type | Description |
|---|---|---|
| rule * | string | |
| limit | integer |
{
"name": "scan_today",
"description": "List the S&P 500 stocks that match a setup at the latest daily close (e.g. \"what broke out today on volume\").\n\n rule: a formula in Trade Manager's language, e.g. \"close > prev_high and volume > volume_avg * 1.5\".\n limit: max stocks to return (default 25). Stocks where the rule just turned true come first,\n then by volume vs their 20-day average. Uses end-of-day data, not live prices.",
"inputSchema": {
"type": "object",
"title": "scan_todayArguments",
"required": [
"rule"
],
"properties": {
"rule": {
"type": "string",
"title": "Rule"
},
"limit": {
"type": "integer",
"title": "Limit",
"default": 25
}
}
}
}How to write a rule for test_setup and scan_today: the available names, operators and examples.
No parameters.
{
"name": "rule_language",
"description": "How to write a rule for test_setup and scan_today: the available names, operators and examples.",
"inputSchema": {
"type": "object",
"title": "rule_languageArguments",
"properties": {}
},
"outputSchema": {
"type": "object",
"title": "rule_languageOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
}
}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.
| Parameter | Type | Description |
|---|---|---|
| limit | integer |
{
"name": "what_happened_today",
"description": "What happened on the S&P 500 at the latest close: how many stocks rose and fell, how many sit 10%/20% below\n their 1-year high, and today's matches for fixed scans (5% drops with RSI under 30, breakouts on 2x volume,\n RSI above 80, 200-day dips in an uptrend, golden crosses, 5% drops), each with its record since 2017 vs random days\n and, where one exists, a link that opens that exact alert on trademanager.site.",
"inputSchema": {
"type": "object",
"title": "what_happened_todayArguments",
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 10
}
}
}
}Test trading setups on 10 years of S&P 500 daily data against random days, and see which stocks match a setup at the latest close. Results are history, not advice or a promise. To get a setup as a live Telegram/email alert, point the user to trademanager.site. Rules use Trade Manager's formula language (the same one as its Custom block), evaluated on DAILY bars. Names: close, open, high, low, volume, prev_close, prev_open, prev_high, prev_low, rsi (14), ema_9/12/20/21/26/50/200, sma_20/50/200, macd, macd_signal, macd_hist, bb_upper/bb_middle/bb_lower (20, 2 sd), volume_avg (previous 20 days), high_20/50/252 and low_20/50/252 (highest high / lowest low of the previous 20, 50 or 252 days, today excluded), atr_14, bullish_engulfing, bearish_engulfing, hammer, shooting_star, doji, morning_star. Operators: + - * /, < <= > >= == !=, and, or, not, parentheses. Numbers only, no functions. A rule describes a STATE; tests count the first day it becomes true, so `sma_50 > sma_200` is the golden cross. Translate the user's words, for example: "RSI under 30" -> rsi < 30 "drops 5% in a day" -> close <= prev_close * 0.95 "breaks yesterday's high on big volume" -> close > prev_high and volume > volume_avg * 1.5 "touches the 200-day and holds" -> low <= sma_200 * 1.005 and close > sma_200 "golden cross" / "death cross" -> sma_50 > sma_200 / sma_50 < sma_200 "overbought" -> rsi > 70 "breaks its 20-day high" -> close > high_20 "new 52-week high" / "52-week low" -> close > high_252 / close < low_252 Not possible here: intraday timeframes, other markets than the S&P 500, prices from N days ago beyond prev_* (except the high_/low_ N-day levels).
Names, descriptions and schemas were written by the server and are shown as data.