canli-mcp / Quant finance

Realized volatility and jumps

From intraday returns per day, compute realized variance, bipower variation, the jump component and the Barndorff-Nielsen-Shephard jump test (tripower quarticity), realized semivariances, realized skewness and kurtosis, and the daily series for HAR forecasts.

The tool is realized_volatility_measures 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
intraday_returnsyesnumber[][]
jump_levelnonumber
periods_per_yearnonumber
include_seriesnoboolean

How a model reaches it

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

Words that find it

Besides its name, title and description, find_tool matches a question to realized_volatility_measures on these words: realized, volatility, variance, bipower, variation, jump, test, bns, tripower, semivariance, intraday, high, frequency.

More

Nothing here is investment advice.