patternfetch
This server provides token-compact crypto market analysis for AI agents, turning a ticker + timeframe into structured, interpreted market intelligence without dumping raw OHLCV data into context.
patternfetch_brief— Get a full market-state brief for any crypto pair and timeframe, including compact candle representation, detected chart/candlestick patterns with confidence scores, support/resistance levels, trend/regime analysis, interpreted indicators (RSI/EMA state), and a one-line natural language summary.patternfetch_delta— Poll a market efficiently by fetching only what changed since the last brief (trend flips, new patterns, RSI-state changes), minimizing token usage; returnschanged=falsewhen nothing material has shifted.patternfetch_analogs— Find historical price windows that resemble the current setup and return the full distribution of outcomes (win-rate, median, min, max, sample size) over a configurable forward horizon.patternfetch_capabilities— List all supported assets, timeframes, endpoints, and usage limits.Create API Keys — Generate a self-serve API key with a small amount of free credit.
⚠️ All outputs are impersonal market data for informational purposes only — not investment advice.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@patternfetch get a brief for BTC/USDT on 4h timeframe"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
patternfetch
patternfetch is a market-data API for AI agents covering US stocks, ETFs and crypto spot. One
call with a ticker and a timeframe returns a token-compact market-state report: compact candles,
detected chart and candlestick patterns, support and resistance levels, market regime, and
interpreted indicators (RSI, EMA). Every detected pattern carries its backtested historical hit rate
and its lift against the pattern-free baseline of the same market, so an agent can tell a
pattern that carries information from one that does not. Six tools — brief, multi, delta,
analogs, scan, capabilities — reachable over REST and MCP, with one-click OAuth, credit
billing via Stripe or x402 USDC on Base, a keyless demo endpoint, and $3 starter credit on signup.
Impersonal market data, not investment advice.
Why it's smaller: for BTC/USDT 4h (120 candles), a raw OHLCV dump is ~3,260 tokens of just numbers the model still has to analyze; patternfetch's interpreted analysis is ~1,323 tokens, already decided. Reproduce it (no account needed).
Coverage: US stocks and ETFs (split- and dividend-adjusted, delayed/EOD, via Yahoo), crypto spot (realtime, via Binance).
Timeframes:
1m,5m,15m,30m,1h,4h,1d,1w.Access: REST at
patternfetch.com/v1/*, MCP atpatternfetch.com/mcp(Streamable HTTP), plus a local stdio bridge (patternfetch-mcp).
Why base rates and lift
A detector that only reports double_top, confidence 0.92 tells an agent nothing about whether that
pattern has ever meant anything. patternfetch attaches an evidence block to each detected pattern:
{
"name": "double_top",
"confidence": 0.92,
"evidence": {
"scope": "US stocks & ETFs",
"tf": "1d",
"band": "0.75-1.00",
"horizon": 10,
"n": 7508,
"hitRate": 0.431,
"ci95": 0.011,
"lift": {
"baseline": 0.419979,
"baselineN": 46038,
"lift": 0.011021,
"ci95": 0.012075,
"informative": false,
"reading": "indistinguishable-from-baseline"
}
}
}hitRate is the realizable gross directional base rate: the fraction of non-overlapping historical
occurrences of that pattern, in that timeframe and confidence band, whose close-to-close return over
the next horizon bars went the expected direction. The forward window starts at detection, so
there is no lookahead. No stops, fees or slippage are modelled.
lift compares that hit rate against the baseline of the same market with no pattern present. Many
patterns come back indistinguishable-from-baseline — that is the honest result, and reporting it
is the point. An agent can filter on informative instead of trusting a geometric confidence score.
Calibration. Across 105 audited categories, 3 fall outside their confidence interval — fewer than the ~5.3 that chance alone predicts across 105 comparisons. For US stocks it is 0 of 60. Method and full tables: patternfetch.com/pattern-base-rates-study. The measurement is reproducible with the open-source honest-signals tool.
Related MCP server: coin-mcp
Quickstart
No key required — the demo endpoint is public:
curl -X POST https://patternfetch.com/v1/demo \
-H 'content-type: application/json' \
-d '{"ticker":"AAPL","timeframe":"1d"}'With a key (self-serve, $3 starter credit):
curl -X POST https://patternfetch.com/v1/keys -d '{"email":"you@example.com"}'
curl -X POST https://patternfetch.com/v1/brief \
-H 'authorization: Bearer pf_...' \
-H 'content-type: application/json' \
-d '{"ticker":"BTC/USDT","timeframe":"4h"}'JavaScript client:
npm install patternfetchimport { Patternfetch } from 'patternfetch';
const { key } = await new Patternfetch().createKey('you@example.com');
const pf = new Patternfetch({ apiKey: key });
const brief = await pf.brief({ ticker: 'AAPL', timeframe: '1d' });
console.log(brief.analysis.nl);
// "AAPL: uptrend (strong), +0.14% last 1d, RSI 71.66 (overbought),
// bearish_engulfing (conf 1, hist 41% over 10b, lift -0.7pp vs 42% base (within noise))."
for (const p of brief.analysis.patterns) {
if (p.evidence?.lift.informative) console.log(p.name, p.evidence.hitRate, p.evidence.lift.lift);
}Tools
Six tools, the same set over MCP (patternfetch_*) and REST (POST /v1/*).
Tool | What it returns | When an agent calls it |
| Market-state report for one ticker + timeframe: compact candles, patterns with base rate and lift, support/resistance, regime, RSI/EMA, one-line summary. | The default. It needs the current technical picture of one market without dumping raw OHLCV into context. |
| One brief per timeframe (default | It wants to know whether a setup is confirmed or contradicted across horizons, without three separate |
| Only what changed since the last brief for that ticker + timeframe — trend flips, new patterns, RSI-state changes. Returns | It polls the same market repeatedly. Call |
| Historical windows whose shape resembles current price action, with the full distribution of what followed: win rate, median, mean, min, max and n over a fixed forward horizon. | It wants the historical outcome spread for a setup rather than a point estimate. Not a prediction, not a strategy backtest. |
| Screener over a curated universe of liquid US large-caps, core and sector ETFs and major crypto pairs. Filter by asset class, regime, pattern and minimum base rate; rows return ranked by base rate with 95% CI. Precomputed daily. | It needs to find candidates across the market rather than analyse a ticker it already named. Feed the shortlist into |
| Supported assets, timeframes, endpoints, limits and pricing. No input. | First, before relying on any assumption about coverage. |
Client methods
Method | Endpoint |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
MCP
patternfetch is a remote MCP server (Streamable HTTP) at https://patternfetch.com/mcp.
Tools: patternfetch_brief, patternfetch_multi, patternfetch_delta, patternfetch_analogs,
patternfetch_scan, patternfetch_capabilities.
Discovery (initialize, tools/list) is free — no key. Only tools/call needs auth.
One-click OAuth (nothing to paste) — in Claude Code, Claude Desktop, Cursor or Smithery, add the URL and authorize once; a free-tier key is minted for you:
claude mcp add --transport http patternfetch https://patternfetch.com/mcpIn claude.ai: Customize → Connectors → Add custom connector → https://patternfetch.com/mcp → Authorize.
Or with a Bearer key — add to your MCP config:
{
"mcpServers": {
"patternfetch": {
"url": "https://patternfetch.com/mcp",
"headers": { "Authorization": "Bearer pf_..." }
}
}
}Get a free key (small starter credit) at https://patternfetch.com/v1/keys.
Local stdio bridge
Prefer a local stdio server (Claude Desktop, sandboxes, no inbound HTTP)? This package
ships patternfetch-mcp, a zero-dependency stdio↔HTTP bridge that exposes the same tools
and forwards calls to patternfetch.com:
{
"mcpServers": {
"patternfetch": {
"command": "npx",
"args": ["-y", "patternfetch-mcp"],
"env": { "PATTERNFETCH_API_KEY": "pf_..." }
}
}
}tools/list works with no key and falls back to the embedded snapshot
(mcp-tools.json) when the remote is unreachable, so introspection always
succeeds. Tool calls use PATTERNFETCH_API_KEY, OAuth or x402. Override the endpoint with
PATTERNFETCH_MCP_URL.
Refresh the snapshot from the live server:
curl -s -X POST https://patternfetch.com/mcp \
-H 'content-type: application/json' \
-H 'accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'Pricing
$3 starter credit on signup, at least $0.50 of it usable immediately without a card. After that, pay per call from credit, topped up via Stripe or x402 USDC on Base. Studio plan: $19/month including $25 of usage.
Call | Price |
| $0.010 |
| $0.025 |
| $0.008 ($0.001 when nothing changed) |
| $0.005 |
| $0.050 |
| $0.020 |
Live figures: GET /v1/platforms.
Legal
patternfetch provides impersonal market data and algorithmic signals for informational purposes only. NOT investment, financial, legal or tax advice, and not a recommendation to buy, sell or hold any security or crypto-asset. Outputs are not personalized to you. Base rates are gross directional frequencies without stops, fees or slippage; past performance and historical analogs do not guarantee future results. Markets are volatile — you may lose all capital. Do your own research. See patternfetch.com/disclaimer, /methodology and /terms.
Available Tools
4 toolspatternfetch_analogsAInspect
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. Impersonal data, not advice.
Inputs: ticker (required), timeframe (required), window, horizon.
patternfetch_briefAInspect
Get a token-compact market-state brief for a crypto ticker + timeframe. Returns compact candles, detected chart/candlestick patterns with geometric confidence, support/resistance levels, trend/regime, and interpreted indicators (RSI/EMA state) plus a one-line summary. 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, portfolio advice, or non-crypto assets. Example: {"ticker":"BTC/USDT","timeframe":"4h"}. Output is impersonal market data, NOT investment advice.
Inputs: ticker (required), timeframe (required), limit.
patternfetch_capabilitiesAInspect
List supported assets, timeframes, endpoints, and limits for patternfetch.
Inputs: no named parameters.
patternfetch_deltaAInspect
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. Returns changed=false when nothing material changed. Impersonal data, not advice.
Inputs: ticker (required), timeframe (required), limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a distinct purpose: patternfetch_analogs provides historical pattern matching, patternfetch_brief gives a current market summary, patternfetch_capabilities lists supported features, and patternfetch_delta reports changes since the last brief. No two tools overlap in functionality.
All tool names follow the pattern 'patternfetch_' followed by a descriptive noun (analogs, brief, capabilities, delta). The naming is uniformly lowercase with underscores, making it predictable and easy to understand.
With only 4 tools, the server is tightly scoped to its domain of pattern analysis. This number is appropriate given the focused nature of the server, providing essential functionality without unnecessary complexity.
The tools cover the full lifecycle of pattern analysis: understanding capabilities, getting a current brief, detecting changes, and retrieving historical analogs. There are no obvious gaps for the intended use case of market analysis.
Maintenance
Related MCP Connectors
Unlock the power of real-time cryptocurrency data with our Crypto Price Insights MCP server.
Crypto market intelligence, token rug-checks, and wallet verification in one MCP server.
MCP server for accessing Glypse's prediction market analytics and research.
MCP server with quote and live cryptocurrency price tools, local and cloud-deployed transports.
Related MCP Servers
- AlicenseBqualityBmaintenanceA Model Context Protocol (MCP) server that provides comprehensive cryptocurrency analysis using the CoinCap API. This server offers real-time price data, market analysis, and historical trends through an easy-to-use interface.3366 npm41MIT
- AlicenseAqualityDmaintenanceA comprehensive cryptocurrency market-data MCP server with 49 tools across six data sources, enabling LLMs to answer market questions via natural language.49MIT
- FlicenseNot gradedqualityCmaintenanceA remote Model Context Protocol (MCP) server for real-time cryptocurrency and stock market analysis. Provides AI-powered market intelligence tools with 9 theory-based analysis engines, multi-chain DEX discovery, and enterprise features.-
- FlicenseNot gradedqualityDmaintenanceA research-only MCP server providing read-only data, analytics, and intelligence for Polymarket BTC 5-minute Up/Down markets, enabling LLM agents to query market snapshots, performance metrics, and strategy candidates.-