patternfetch — Market-State Briefs for AI Trading Agents
patternfetch
One API/MCP call turns a crypto ticker + timeframe into a token-compact market-state brief — so an LLM trading agent never has to dump raw OHLCV into its context.
Instead of hundreds of raw candles per ticker, you get: compact candles + a SAX shape signature, detected chart/candlestick patterns (double top/bottom, head & shoulders, engulfing, hammer, doji), support/resistance clusters, a regime label, and interpreted indicators (RSI / EMA / ATR) — plus a one-line summary. Crypto-first. Impersonal and non-directive by design — data, never buy/sell advice.
Why
Feeding raw OHLCV into the model context is huge, slow, and the model re-derives the same structure every single call. patternfetch does that work server-side and hands back a brief that's a fraction of the tokens.
Endpoints
| Method | Path | Price | Returns |
|---|---|---|---|
| POST | /v1/brief | $0.01 | full market-state brief (candles + patterns + S/R + regime + indicators + summary) |
| POST | /v1/delta | $0.008 ($0.001 if unchanged) | only what changed since your last brief (token-minimal polling) |
| POST | /v1/candles | $0.005 | compact candle codec only (rows + SAX shape signature) |
| POST | /v1/analogs | $0.05 | historical analogs as a full outcome distribution (n, win-rate, median, min, max) |
| POST | /v1/keys | free | self-serve API key + $0.05 credit |
| GET | /v1/platforms | free | capability matrix (assets, timeframes) |
MCP config (remote, streamable-http)
{
"mcpServers": {
"patternfetch": {
"url": "https://patternfetch.com/mcp",
"headers": { "Authorization": "Bearer YOUR_PATTERNFETCH_KEY" }
}
}
}
Get a key: curl -X POST https://patternfetch.com/v1/keys -H "Content-Type: application/json" -d '{"email":"you@example.com"}'
Example
curl -X POST https://patternfetch.com/v1/brief \
-H "Authorization: Bearer <key>" -H "Content-Type: application/json" \
-d '{"ticker":"BTC","timeframe":"1h"}'
Payment
Pay per call via x402 (USDC on Base, no account) or Stripe (cards). Every response includes an exact cost block.
- Website: https://patternfetch.com
- Not investment advice. Impersonal market data only.
**Schritt für Schritt im Formular:**
1. Name → `patternfetch`
2. Title → obige Zeile
3. Type → `server`
4. Tags → obige Liste
5. Avatar URL → `https://github.com/MarvinRey7879.png`
6. Server config → die Remote-JSON von vorhin
7. Content → obiger Markdown-Block
8. Absenden.
Server Config
{
"mcpServers": {
"patternfetch": {
"url": "https://patternfetch.com/mcp",
"headers": {
"Authorization": "Bearer YOUR_PATTERNFETCH_KEY"
}
}
}
}Recommend Servers
View All高德地图官方 MCP Server
summarize chat message
test