canli-mcp / Quant finance

Trend-scanning labels

Label each period by the strongest forward trend: regress prices on time over every forward window in a range, keep the window with the largest |t-statistic| of the slope, and label by its sign with the t-statistic as confidence (Lopez de Prado's trend scanning).

The tool is trend_scanning_labels 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[]
min_windownointeger
max_windownointeger
stepnointeger
include_rowsnoboolean

How a model reaches it

Ask in plain words. The model finds trend_scanning_labels 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": "trend_scanning_labels",
  "arguments": {
    "prices": "<number[]>"
  }
}

Words that find it

Besides its name, title and description, find_tool matches a question to trend_scanning_labels on these words: trend, scanning, labels, t, statistic, slope, forward, window, labeling, machine, learning, label, confidence.

More

Nothing here is investment advice.