canli-mcp / Quant finance

Rolling beta

Compute a rolling-window beta (and correlation) of returns against a benchmark: latest, average, minimum and maximum, optionally the full series.

The tool is rolling_beta 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
returnsyesnumber[]
benchmarkyesnumber[]
windowyesinteger
include_seriesnoboolean

How a model reaches it

Ask in plain words. The model finds rolling_beta 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": "rolling_beta",
  "arguments": {
    "returns": "<number[]>",
    "benchmark": "<number[]>",
    "window": "<integer>"
  }
}

Words that find it

Besides its name, title and description, find_tool matches a question to rolling_beta on these words: rolling, beta, correlation, window, time, varying, market, exposure.

More

Nothing here is investment advice.