canli-mcp / Quant finance

Weights for overlapping labels

Weight labels whose spans overlap so a model does not over-count the same information: concurrency per period, each label's average uniqueness, return-attribution weights, and optional time decay (Lopez de Prado, chapter 4).

The tool is sample_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[]
spansyesany[][]
decaynonumber

How a model reaches it

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

Words that find it

Besides its name, title and description, find_tool matches a question to sample_weights on these words: sample, weights, uniqueness, concurrency, overlapping, labels, return, attribution, time, decay, machine, learning, sequential, bootstrap.

More

Nothing here is investment advice.