It makes one call. Send a ticker and a timeframe to POST /v1/brief (or call the MCP tool patternfetch_brief); the API does the detection and returns the patterns it found — each with a confidence score, where it is, and how wide it is. The agent never has to draw a chart, scrape an exchange, or reason over raw candles.
Crypto spot · 1m → 1d · candlestick + chart patterns
One POST /v1/brief — or the MCP tool patternfetch_brief — with { ticker, timeframe } returns the detected candlestick and chart patterns. Each detection carries a geometric confidence (0..1), the candle index it sits on (at), and how many candles it spans (span). The server does the geometry; your agent never has to chart anything or scrape an exchange.
The same brief reports both single/few-candle candlestick patterns and multi-candle chart patterns:
Candlestick patterns (bullish_engulfing, bearish_engulfing, hammer, doji) describe the shape of one or two candles. Chart patterns (double_top, double_bottom, head_and_shoulders) describe a multi-candle formation. Both come back in the same analysis.patterns array, with the wider chart patterns carrying a larger span.
curl -X POST https://patternfetch.com/v1/brief \
-H "Authorization: Bearer pf_…" \
-H "Content-Type: application/json" \
-d '{ "ticker": "BTC/USDT",
"timeframe": "4h" }'
"patterns": [
{ "name": "double_bottom",
"confidence": 0.86,
"at": 158, "span": 14 },
{ "name": "bullish_engulfing",
"confidence": 0.71,
"at": 142, "span": 2 }
]
Each entry tells the agent what was detected (name), how cleanly the geometry matched (confidence, 0..1), where it sits in the series (at = candle index), and how wide it is (span = candles covered). So {"name":"double_bottom","confidence":0.86,"at":158,"span":14} means a high-quality double bottom spanning 14 candles ending around index 158.
That same brief — one call, one price — also returns support/resistance levels, the regime (trend / strength / volatility), interpreted indicators (RSI/EMA state, not just numbers), and a one-line nl summary the agent can act on. Patterns are just one field of the whole market-state brief, so the agent gets the full context in the same round trip.
① No-signup demo — POST /v1/demo returns a real brief (with patterns) and no key. ② Free key with $0.05 starter credit (~5 briefs) from one call, no card. ③ Then pay-per-call: brief $0.01/call. Pay with x402 (USDC on Base, no account) or a Stripe card. Only actual calls are metered. Pricing →
The MCP tool is patternfetch_brief — same input, same patterns array, no HTTP plumbing in your agent. Two ways to connect, both zero-friction:
Add the server URL in Claude.ai, Cursor or Smithery and click Authorize once — patternfetch mints a free-tier key for you automatically, nothing to paste.
# Claude.ai → Settings → Connectors → Add custom connector
https://patternfetch.com/mcp
# click Authorize → free key minted
{
"mcpServers": {
"patternfetch": {
"url": "https://patternfetch.com/mcp",
"headers": { "Authorization": "Bearer pf_…" }
}
}
}
Candlestick patterns: bullish_engulfing, bearish_engulfing, hammer and doji. Chart patterns: double_top, double_bottom and head_and_shoulders. Each detection returns a confidence (0..1), the candle index at, and a span.
It is a geometric quality score from 0 to 1 — how cleanly the candle geometry matches the textbook shape (body/wick ratios for candlesticks; peak/trough symmetry and neckline fit for chart patterns). It is a shape-match score, not a probability of profit or of any future price move.
It works for crypto spot pairs on timeframes from 1m to 1d. Pass a pair like BTC/USDT or ETH/USDT and a timeframe such as 1m, 5m, 15m, 1h, 4h or 1d.
No. It's impersonal market data and algorithmic pattern detections, for informational purposes only — not advice, not personalized, non-executing. See the disclaimer.
Chart pattern detection API · Support/resistance levels API · Technical indicators API · Docs · Try it free