Skip to main content
Glama
aggreyeric

Market Regime Oracle

by aggreyeric

šŸ“Š Market Regime Oracle

A 5-signal → 5-state BTC market-regime classifier with posture mapping, backtested vs buy-and-hold.

Fuses momentum, sentiment, volatility, funding & flow into one explainable regime — and a documented risk posture per regime.

Python License: MIT Tests Track MCP


What It Does

Ask "What kind of BTC market is this, and how much risk should I take?"

The oracle answers with one of 5 regimes + a documented posture:

Regime

Target Exposure

Posture

🟢 RISK_ON

100%

Uptrend — full exposure

🟔 RANGE_BOUND

40%

Sideways — light exposure

šŸ”µ RISK_OFF

20%

Downtrend — defensive

šŸ”“ CAPITULATION

10%

Panic — max defensive

🟣 EUPHORIA

30%

Blow-off — take profit

Built as an MCP Strategy Skill for the CoinMarketCap Agent Hub (BNB AI Trading — Track 2). Any MCP-compatible client (Claude Desktop, Cursor, CMC Agent Hub) calls get_market_regime to get a deterministic, no-look-ahead risk posture.


Related MCP server: PreReason-mcp

šŸ“ˆ Headline Result

In a down year for BTC (āˆ’37%), the regime strategy did āˆ’12.7% — halving drawdown (āˆ’24% vs āˆ’51%) and halving volatility (19% vs 43%), outperforming buy-and-hold by ~25 points while still going long in uptrends.

Metric

Regime Strategy

Buy & Hold

Total return

āˆ’12.7%

āˆ’37.4%

Max drawdown

āˆ’24.2%

āˆ’51.2%

Annualized volatility

19.3%

43.1%

Sharpe (rf 4%)

āˆ’0.82

āˆ’0.97

Sortino

āˆ’1.01

āˆ’1.32

Data: CoinGecko BTC daily (2025-06-19 → 2026-06-17, 364 days). Start $10,000. 10 bps/turnover cost.


šŸ–¼ļø Visual Results

Equity Curve — Regime Strategy vs Buy & Hold

Drawdown — Strategy Stays Shallower

BTC Price with Regime Overlay

Regime Distribution & Target Exposure


šŸ—ļø Architecture

  CoinGecko (BTC OHLCV)         alternative.me (Fear & Greed)
         │                              │
         ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”¬ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜
                        ā–¼
             ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”
             │   data/loader.py    │  aligned daily features
             ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”¬ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜
                       ā–¼
  ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”
  │     5 independent signal modules         │  each → score in [-1, +1]
  │  momentum(0.30)  fear_greed(0.25)        │
  │  funding(0.15)   flows(0.15)   vol(0.15) │
  ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”¬ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜
                         ā–¼ weighted fusion
                  composite score
                         ā–¼ priority rules
  ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”
  │   5-state regime classifier              │  CAPITULATION > EUPHORIA >
  │   (deterministic, no look-ahead)         │  RISK_OFF   > RISK_ON >
  ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”¬ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜                          > RANGE_BOUND
                         ā–¼
                target exposure + action
           ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”“ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”
           ā–¼                               ā–¼
    vectorized backtest                MCP tool: get_market_regime
    (no look-ahead, w/ costs)          (stdio, Agent Hub skill)

🧩 The 5 Signals

Signal

Source

Weight

RSI / MACD momentum

CoinGecko price

0.30

Fear & Greed Index

alternative.me

0.25

Volatility regime

CoinGecko price

0.15

Funding rate proxy

derived from price

0.15

Exchange flow proxy

derived from volume

0.15

Each signal outputs a normalized bullishness score in [-1, +1]. All 5 are independently unit-tested.

Transparency: Funding rate and exchange flows have no free public feed. We reconstruct them from price/volume data as clearly-labeled proxies. Drop in real feeds anytime — the fusion layer is signal-agnostic.


šŸš€ Quick Start

git clone https://github.com/aggreyeric/bnb-market-regime-oracle.git
cd bnb-market-regime-oracle
pip install -r requirements.txt

# Run full pipeline: fetch → classify → backtest → charts
python main.py

# Run tests (offline, no network needed)
PYTHONPATH=src python -m pytest tests/

# Run as MCP server
PYTHONPATH=src python -m market_regime_oracle.mcp_server

# Live MCP demo (30 seconds)
./scripts/demo.sh

Docker

docker compose up --build run    # full pipeline
docker compose up --build server # MCP server

šŸ“ Project Layout

market_regime_oracle/
ā”œā”€ā”€ src/market_regime_oracle/
│   ā”œā”€ā”€ data/          # CoinGecko + alternative.me loaders
│   ā”œā”€ā”€ signals/       # 5 signal modules (unit-tested)
│   ā”œā”€ā”€ classifier/    # fusion → regime mapping
│   ā”œā”€ā”€ backtest/      # vectorized engine, no look-ahead
│   ā”œā”€ā”€ viz/           # equity/drawdown/regime charts
│   └── mcp_server.py  # MCP stdio server
ā”œā”€ā”€ tests/             # 24/24 passing
ā”œā”€ā”€ results/           # CSVs, metrics.json, PNG charts
ā”œā”€ā”€ scripts/demo.sh    # live MCP round-trip
ā”œā”€ā”€ Dockerfile
ā”œā”€ā”€ docker-compose.yml
└── README.md

šŸ“š Data Sources

  • CoinGecko v3 free API — BTC daily close + volume

  • alternative.me — Fear & Greed Index

Both public, both free. No API keys required.


šŸ“œ License

MIT Ā© 2026

šŸ¤– AI Assistants

→ See CLAUDE.md for AI coding assistant context.

A
license - permissive license
-
quality - not tested
B
maintenance

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • F
    license
    -
    quality
    D
    maintenance
    AI-powered crypto signal intelligence for 20 assets (BTC, ETH, SOL, etc). 6 scoring dimensions: whale activity, technical analysis, derivatives flow, narrative strength, sentiment, market structure. Market regime detection (TRENDING/RANGING), portfolio optimization, and accuracy tracking. 9 read-only MCP tools. Free via MCP, $0.001 USDC via x402 on Base for REST API.
    Last updated
    2
  • A
    license
    A
    quality
    D
    maintenance
    Pre-reasoned Bitcoin and macro market briefings with trend signals, confidence scores, and regime classification. 17 briefings covering BTC, Fed balance sheet, M2, Treasury yields, and cross-asset correlations.
    Last updated
    5
    79
    4
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Deterministic risk governance for crypto trading agents. 5-level policy engine with position sizing, leverage limits, and trade blocking. One tool: get_risk_policy. Supports BTC and ETH.
    Last updated
    1
    19
    1
    MIT

View all related MCP servers

Related MCP Connectors

  • Crypto regime classifier for trading agents. 100% bounded regime accuracy. 50 free calls/day.

  • Crypto market intelligence: regime detection, funding rates, liquidations, prices, signals.

  • Pre-reasoned Bitcoin & macro financial briefings for AI agents. Trend signals, regimes, 17 contexts.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/aggreyeric/bnb-ai-trading-agent'

If you have feedback or need assistance with the MCP directory API, please join our Discord server