canli-mcp / Quant finance

Backtest z-score mean reversion

Backtest mean reversion on a rolling z-score of price: buy stretched lows (and short stretched highs), exit near the mean, with costs.

The tool is backtest_zscore_reversion in canli-mcp 0.22.0, free and MIT-licensed, with no account and no API key. It comes from canli-quant-mcp, which canli-mcp includes, and it is also its own server.

Arguments

As the server declares them
ArgumentRequiredType
pricesyesnumber[]
windownointeger
entry_znonumber
exit_znonumber
curvenoboolean
datesnostring[]
cost_bpsnonumber
periods_per_yearnonumber
risk_freenonumber
long_onlynoboolean

How a model reaches it

Ask in plain words. The model finds backtest_zscore_reversion with canli-mcp's find_tool, reads its arguments with describe_tool if it needs to, and runs it with run_tool. The call has this shape, with your values in place of the angle brackets:

{
  "name": "backtest_zscore_reversion",
  "arguments": {
    "prices": "<number[]>"
  }
}

Words that find it

Besides its name, title and description, find_tool matches a question to backtest_zscore_reversion on these words: mean, reversion, z, score, bollinger, reversal, backtest, oversold.

More

Nothing here is investment advice.