MCP.so
Sign In

patternfetch — Market-State Briefs for AI Trading Agents

@MarvinRey7879

Repository

About patternfetch — Market-State Briefs for AI Trading Agents

patternfetch — token-compact market-state briefs for AI trading agents. One call: compact candles + patterns + support/resistance + regime + interpreted indicators. MCP + REST, x402 + Stripe. github.com/MarvinRey7879/patternfetch-client

#trading#crypto#finance#market-data#technical-analysis#ai-agents#x402#rest-api

Basic information

Category

Finance & Commerce

Transports

stdio

Publisher

MarvinRey7879

Submitted by

MarvinRey7879

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "patternfetch": {
      "url": "https://patternfetch.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_PATTERNFETCH_KEY"
      }
    }
  }
}

Tools

5

Get a token-compact market-state brief for a stock, ETF, or crypto ticker + timeframe. Returns compact candles, detected chart/candlestick patterns with geometric confidence AND a backtested historical base rate (how often that pattern+timeframe+confidence-band actually resolved its way), support/resistance levels, trend/regime, and interpreted indicators (RSI/EMA state) plus a one-line summary. Covers US stocks/ETFs (split & dividend adjusted, delayed/EOD) and crypto spot (realtime). WHEN: an agent needs the current technical picture of a market without dumping raw OHLCV into context (saves tokens, avoids numeric hallucination). WHEN NOT: you need order execution or portfolio advice. Examples: {"ticker":"AAPL","timeframe":"1d"}, {"ticker":"BTC/USDT","timeframe":"4h"}. Output is impersonal market data, NOT investment advice.

Get a multi-timeframe market-state view for one stock, ETF, or crypto ticker in a single call: a token-compact brief for each requested timeframe (default 1h, 4h, 1d) PLUS a cross-timeframe alignment read — whether the trends across timeframes agree or diverge, with the split spelled out (e.g. "1h up / 4h up / 1d down"). WHEN: an agent wants to know if a setup is confirmed across horizons or conflicting between them, without making 3 separate brief calls. WHEN NOT: you only care about one timeframe (use brief). The alignment/divergence is impersonal DESCRIPTIVE data, not a signal to act on. Example: {"ticker":"BTC/USDT","timeframes":["1h","4h","1d"]}. Not investment advice.

Get only what CHANGED since your last brief for a ticker+timeframe (trend flips, new patterns, RSI-state changes). WHEN: an agent polls the same market repeatedly and wants minimal tokens — call brief once, then delta on each later poll. WHEN NOT: first look at a market (use brief). Returns changed=false when nothing material changed. Example: {"ticker":"BTC/USDT","timeframe":"4h"}. Impersonal data, not advice.

Find historical windows whose shape resembles the current price action and return the FULL distribution of what followed (win-rate, median, min, max, n) over a fixed forward horizon. WHEN: an agent wants historical context for a setup. NOT a prediction, NOT a backtest of a strategy; past distribution does not guarantee future results. Example: {"ticker":"ETH/USDT","timeframe":"1d"}. Impersonal data, not advice.

Call this FIRST to discover supported assets, timeframes, endpoints, and limits before calling brief/delta/analogs. No input required.

Overview

What is patternfetch?

patternfetch is an MCP server that turns a crypto ticker and timeframe into a token-compact market-state brief for LLM trading agents. It replaces raw OHLCV data with compact candles, SAX shape signatures, detected chart and candlestick patterns, support/resistance clusters, regime labels, and interpreted indicators (RSI/EMA/ATR), plus a one-line summary. Crypto-first and impersonal — it provides data, not buy/sell advice.

How to use patternfetch?

Configure the MCP client as a remote streamable-http server using the URL https://patternfetch.com/mcp and an Authorization header with a Bearer token. Obtain an API key by sending a POST request to /v1/keys with your email. Then send ticker and timeframe parameters to endpoints like /v1/brief to retrieve a full brief, or use /v1/delta for token-minimal polling.

Key features of patternfetch

  • Compact candle codec with SAX shape signature per ticker
  • Detected chart patterns (double top/bottom, head & shoulders, engulfing, hammer, doji)
  • Support/resistance clusters and market regime labels
  • Interpreted indicators (RSI, EMA, ATR) with a one-line summary
  • Token-minimal polling via /v1/delta endpoint (cheaper if unchanged)
  • Pay-per-call via x402 (USDC on Base) or Stripe

Use cases of patternfetch

  • AI trading agents needing structured market-state briefs without raw OHLCV
  • Token-constrained LLM context optimization for multi-ticker analysis
  • Efficient polling of price state changes using delta updates
  • Historical outcome distribution for backtesting via /v1/analogs

FAQ from patternfetch

What are the different endpoints and their costs?

/v1/brief ($0.01) returns the full brief; /v1/delta ($0.008, $0.001 if unchanged) returns only changes from the last brief; /v1/candles ($0.005) returns only compact candles; /v1/analogs ($0.05) returns historical analog outcomes; /v1/keys (free) provides a key with $0.05 credit.

How do I pay for calls?

Payment is per call via x402 (USDC on Base, no account required) or Stripe credit cards. Every response includes an exact cost block.

Is patternfetch investment advice?

No. It provides impersonal market data only. The server is non-directive by design — it never gives buy/sell advice.

How do I get an API key?

Send a POST to https://patternfetch.com/v1/keys with a JSON body containing your email (e.g., {"email":"[email protected]"}). You will receive a key to use in the Authorization header.

What assets and timeframes are supported?

The /v1/platforms endpoint returns a free capability matrix listing all supported assets (crypto tickers) and available timeframes.

Comments

More Finance & Commerce MCP servers

Edwin

edwin-finance

Empowering AI agents to dominate DeFAI

64

Awesome Crypto MCP Servers

badkk

A collection of crypto MCP servers.

139

Financial Modeling Prep MCP (Model Context Protocol)

imbenrabi

A Model Context Protocol (MCP) implementation for Financial Modeling Prep, enabling AI assistants to access and analyze financial data, stock information, company fundamentals, and market insights.

139

Boba MCP

Able-labs-xyz

Boba CLI - The bridge between agents and decentralized trading.

56

MCP Yahoo Finance

maxscheijen

A Model Context Protocol (MCP) server for Yahoo Finance.

27