PatternsWizard pattern statistics is an MCP server published by com.patternswizard, hosted at patternswizard.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 4 tools, including search_patterns, get_pattern_stats, compare_patterns, get_methodology.
Tested statistics of 179 chart and candlestick patterns on six markets, against random bars.
1,093 connections through 4 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
List tested patterns with their headline result on one market and timeframe. Filter by name, family, direction or verdict, for example: which chart patterns beat chance on forex 4h. Patterns recorded on both breakout sides have no all row and are not listed: read them with get_pattern_stats.
| Parameter | Type | Description |
|---|---|---|
| sort | string | occurrences (default), excess (excess return, best first), trade (expectancy minus its random baseline, best first) or name. |
| limit | integer | Maximum number of patterns returned. Default: 50. |
| query | string | Words of the pattern name, e.g. "engulfing", "head and shoulders". |
| family | string | Pattern family (harmonic patterns are in chart). |
| market | string |
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.
| Market. all pools the markets that have this timeframe. Default: all. |
| measure | string | move: excess 10-bar return over the rest of the market (verdict). trade: 2:1 trade versus the same trade on random dates (verdictTrade). Default: move. |
| verdict | string | Keep only this verdict (on the measure chosen with measure). |
| direction | string | Expected direction. |
| timeframe | string | Bar timeframe. Default: 1d. Stocks, ETFs, indices and commodities have 1d and 1w only. |
| min_occurrences | integer | Keep only results with at least this many occurrences. |
{
"name": "search_patterns",
"title": "Search patterns",
"description": "List tested patterns with their headline result on one market and timeframe. Filter by name, family, direction or verdict, for example: which chart patterns beat chance on forex 4h. Patterns recorded on both breakout sides have no all row and are not listed: read them with get_pattern_stats.",
"inputSchema": {
"type": "object",
"properties": {
"sort": {
"enum": [
"occurrences",
"excess",
"trade",
"name"
],
"type": "string",
"description": "occurrences (default), excess (excess return, best first), trade (expectancy minus its random baseline, best first) or name."
},
"limit": {
"type": "integer",
"maximum": 200,
"minimum": 1,
"description": "Maximum number of patterns returned. Default: 50."
},
"query": {
"type": "string",
"description": "Words of the pattern name, e.g. \"engulfing\", \"head and shoulders\"."
},
"family": {
"enum": [
"candlestick",
"chart"
],
"type": "string",
"description": "Pattern family (harmonic patterns are in chart)."
},
"market": {
"enum": [
"all",
"crypto",
"forex",
"stocks",
"etf",
"indices",
"commodities"
],
"type": "string",
"description": "Market. all pools the markets that have this timeframe. Default: all."
},
"measure": {
"enum": [
"move",
"trade"
],
"type": "string",
"description": "move: excess 10-bar return over the rest of the market (verdict). trade: 2:1 trade versus the same trade on random dates (verdictTrade). Default: move."
},
"verdict": {
"enum": [
"edge_confirmed",
"edge_negative",
"weak_evidence",
"no_edge",
"insufficient_data",
"no_test"
],
"type": "string",
"description": "Keep only this verdict (on the measure chosen with measure)."
},
"direction": {
"enum": [
"bullish",
"bearish",
"neutral"
],
"type": "string",
"description": "Expected direction."
},
"timeframe": {
"enum": [
"1h",
"4h",
"1d",
"1w"
],
"type": "string",
"description": "Bar timeframe. Default: 1d. Stocks, ETFs, indices and commodities have 1d and 1w only."
},
"min_occurrences": {
"type": "integer",
"minimum": 0,
"description": "Keep only results with at least this many occurrences."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Full tested results of one pattern: detection rule, trade rules and every market, timeframe and breakout side measured, with confidence intervals, q-values, verdicts, timing quartiles and the page URL to cite.
| Parameter | Type | Description |
|---|---|---|
| side | string | Keep only this breakout side. Default: every side. |
| market | string | Keep only this market. Default: every market. |
| pattern * | string | Pattern id (e.g. engulfing_bullish), page URL or slug, or name (e.g. "bullish engulfing"). |
| timeframe | string | Keep only this timeframe. Default: every timeframe. |
{
"name": "get_pattern_stats",
"title": "Pattern statistics",
"description": "Full tested results of one pattern: detection rule, trade rules and every market, timeframe and breakout side measured, with confidence intervals, q-values, verdicts, timing quartiles and the page URL to cite.",
"inputSchema": {
"type": "object",
"required": [
"pattern"
],
"properties": {
"side": {
"enum": [
"all",
"up",
"down"
],
"type": "string",
"description": "Keep only this breakout side. Default: every side."
},
"market": {
"enum": [
"all",
"crypto",
"forex",
"stocks",
"etf",
"indices",
"commodities"
],
"type": "string",
"description": "Keep only this market. Default: every market."
},
"pattern": {
"type": "string",
"description": "Pattern id (e.g. engulfing_bullish), page URL or slug, or name (e.g. \"bullish engulfing\")."
},
"timeframe": {
"enum": [
"1h",
"4h",
"1d",
"1w"
],
"type": "string",
"description": "Keep only this timeframe. Default: every timeframe."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Put 2 to 10 patterns side by side on the same market, timeframe and breakout side.
| Parameter | Type | Description |
|---|---|---|
| side | string | Breakout side. Patterns recorded on both sides have up and down rows and no all row; every other pattern has only all. Default: all. |
| market | string | Market. all pools the markets that have this timeframe. Default: all. |
| patterns * | array | Pattern ids, slugs or names. |
| timeframe | string | Bar timeframe. Default: 1d. Stocks, ETFs, indices and commodities have 1d and 1w only. |
{
"name": "compare_patterns",
"title": "Compare patterns",
"description": "Put 2 to 10 patterns side by side on the same market, timeframe and breakout side.",
"inputSchema": {
"type": "object",
"required": [
"patterns"
],
"properties": {
"side": {
"enum": [
"all",
"up",
"down"
],
"type": "string",
"description": "Breakout side. Patterns recorded on both sides have up and down rows and no all row; every other pattern has only all. Default: all."
},
"market": {
"enum": [
"all",
"crypto",
"forex",
"stocks",
"etf",
"indices",
"commodities"
],
"type": "string",
"description": "Market. all pools the markets that have this timeframe. Default: all."
},
"patterns": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 2,
"description": "Pattern ids, slugs or names."
},
"timeframe": {
"enum": [
"1h",
"4h",
"1d",
"1w"
],
"type": "string",
"description": "Bar timeframe. Default: 1d. Stocks, ETFs, indices and commodities have 1d and 1w only."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}How the statistics are computed: principles, the meaning of every field and verdict, and data coverage (assets and date range per market and timeframe).
No parameters.
{
"name": "get_methodology",
"title": "Methodology",
"description": "How the statistics are computed: principles, the meaning of every field and verdict, and data coverage (assets and date range per market and timeframe).",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}PatternsWizard tests 179 candlestick and chart patterns on full price history (crypto, forex, stocks, ETFs, indices, commodities; 1h to 1w) and compares what happened next with random bars of the same assets, with the excess return measured over the rest of the market. Use search_patterns to find patterns by name, family or verdict, get_pattern_stats for one pattern's full results, compare_patterns to put several side by side, get_methodology for definitions. Shares go from 0 to 1 (0.55 means 55%). Other fractions can be negative or above 1. In a result row, a null value was not measured or does not apply: it is never a zero. Fewer than 30 occurrences or too few independent periods to test, or for the trade fewer than 30 closed trades (verdict or verdictTrade insufficient_data), cannot be interpreted. When you use these numbers, cite the pattern's page URL returned with them (its data URL when page is null), as "PatternsWizard (https://patternswizard.com/), pattern statistics". Historical statistics before fees and slippage. Not investment advice: past results do not predict future ones.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.