mcpField
S
StratEvo

StratEvo

Local
github.com/NeuZhouFinance33Updated 28w ago

About StratEvo

StratEvo is a quantitative trading MCP server offering quotes, backtesting, screening, and genetic-algorithm strategy evolution. It targets quant researchers who want strategies validated with walk-forward and overfitting checks rather than a single backtest period.

Key features

  1. 01Quotes, backtesting and factor screening
  2. 02Genetic algorithm evolution of strategy weights
  3. 03Walk-forward out-of-sample validation
  4. 04Monte Carlo and CPCV overfitting checks
  5. 05Paper trading and signal records

Use cases

  1. 01Researching parameters for US stock or crypto strategies
  2. 02Checking strategy robustness across several time windows
  3. 03Tracking daily paper trading returns and drawdowns

MCP support

The project is an MCP server that exposes quote, backtesting and screening capabilities to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"neuzhou-stratevo": {
"command": "uvx",
"args": [
"stratevo"
]
}
}
}
Run commanduvx stratevo

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypistratevo6.0.3

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

🦀 StratEvo

Stop writing trading strategies. Evolve them.

A genetic algorithm engine that breeds and walk-forward validates trading strategies across 484+ market factors.

484+ Evolvable Factors Markets Validation Discord

Live Signals · Paper Trading · How It Works · Results · Robustness · Get Access


📡 Live Signals

Real-time buy/sell signals from evolved strategies. Updated daily. All signals are committed to git history — you can verify every one.

Latest Signals
DateMarketActionAssetEntry PriceDNAStatus
Signals will be posted here as Paper Trading goes live

📁 Full signal history: signals/


📊 Paper Trading Performance

Forward-testing evolved strategies on real market data with simulated execution. No hindsight, no cherry-picking.

Paper Trading active — Crypto V13 live since 2026-04-18.

Current Paper Portfolio
StrategyMarketStart DateDaysReturnSharpeMaxDDTradesStatus
Crypto V13Crypto2026-04-180————🟢 Live

📁 Daily P&L reports: paper-trading/
📈 Equity curves: paper-trading/charts/

Equity Curve (demo — real data accumulating)

Equity Curve

Drawdown

Drawdown


How It Works

Most quant tools make you write the strategy. StratEvo evolves them instead.

You write the rules        →  StratEvo discovers the rules
You tune parameters        →  GA tunes parameters  
You test on one period     →  Walk-forward tests on multiple windows
You hope it generalizes    →  Monte Carlo measures if it does
  Random DNA population (484 factor weights + risk parameters)
       │
       ▼
  ┌──────────────────────┐
  │  Walk-Forward Test   │  Multi-window out-of-sample validation
  │  each DNA candidate  │  Real fees, slippage, position caps
  └──────────┬───────────┘
             │
             ▼
  Keep the survivors (fitness = Sharpe × Return / MaxDD)
             │
             ▼
  Mutate + Crossover → next generation
             │
             ▼
  Repeat for N generations

Each DNA is a weight vector across 484+ factors plus risk/position parameters — all evolvable:

ParameterRangeWhat it controls
Factor weights (×484)0.0–1.0Which factors matter and how much
hold_days2–60Day trades through swing trades
trailing_stop%Trail below peak to lock in profits
market_regimesensitivityReduce exposure automatically in bear markets
kelly_fraction0–1Position sizing from recent win rate

Evolution Results

Numbers from our running evolution engines. Updated as generations progress.

🇺🇸 US Stocks V8 (100 S&P 500 stocks — Gen 136)
MetricBest DNA
Annual Return33.5%
Sharpe Ratio1.47
Max Drawdown17.0%
Win Rate55.5%
Profit Factor1.75
Total Trades179
₿ Crypto V13 (17 assets — Gen 53)
MetricBest DNA
Annual Return69.0%
Sharpe Ratio2.27
Max Drawdown13.0%
Win Rate50.0%
Profit Factor1.58
Total Trades174

These are backtests with walk-forward validation, not live trades. That's the whole point of paper trading — proving it works forward, not just backward.


Anti-Overfitting

We learned this the hard way. An early version showed 25,000% returns. Turned out to be a bug — look-ahead bias.

DefenseWhat it does
Walk-ForwardMulti-window OOS validation. Must profit on data it never trained on.
Monte Carlo1,000 shuffled iterations. p-value < 0.05 or it's luck.
CPCVCombinatorial Purged Cross-Validation. Industry standard for a reason.
Arena ModeMultiple strategies compete head-to-head. Crowded signals get penalized.
Bias DetectionLook-ahead, snooping, survivorship — flagged automatically.
Turnover PenaltyExcessive trading is punished. Real transaction costs baked in.

An honest 33% beats a fake 25,000%.


484+ Factors

CategoryCountExamples
Crypto-Native200Funding rate, whale detection, liquidation cascade
Momentum14ROC, acceleration, trend strength
Volume & Flow13OBV, smart money, Wyckoff VSA
Volatility13ATR, Bollinger squeeze, vol-of-vol
Mean Reversion12Z-score, Keltner channel position
Trend Following14ADX, EMA golden cross, MA fan
Qlib Alpha15811Microsoft Qlib compatible factors
+ 5 more categories37Risk, quality, price structure, sentiment, DRL

All factor weights are discovered by evolution. Zero manual tuning.


Strategy Styles

The algorithm converges on recognizable trading styles on its own:

StyleWhat the DNA learned
Value SeekerBuys cheap, holds patient
Momentum RiderChases runners, dumps laggards
Mean ReverterBets on bounce-backs
Flow ReaderFollows the money — volume leads price
Volatility HunterProfits from vol expansion
Crypto Native200 factors built for 24/7 markets

Get Access

StratEvo Pro includes the evolution engine, paper trading, signal generation, and live exchange connectors.

📧 Contact: [email protected]
💬 Discord: discord.gg/kAQD7Cj8


Technical Papers


Check back daily for updated signals and paper trading results.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.