canli-mcp / Quant finance

Backtest your own target weights

Backtest any strategy from your own target weights per period (decided at each close, applied to the next period) with the same costed, drift-aware engine; null rows mean hold.

The tool is backtest_weights 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[][]
weightsyes(number[]|null)[]
curvenoboolean
datesnostring[]
cost_bpsnonumber
periods_per_yearnonumber
risk_freenonumber
long_onlynoboolean

How a model reaches it

Ask in plain words. The model finds backtest_weights 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_weights",
  "arguments": {
    "prices": "<number[][]>",
    "weights": "<(number[]|null)[]>"
  }
}

Words that find it

Besides its name, title and description, find_tool matches a question to backtest_weights on these words: custom, backtest, target, weights, signals, portfolio, engine, positions, costs, turnover.

More

Nothing here is investment advice.