canli-mcp / Quant finance
Probabilistic Sharpe ratio
Compute the probability that the true Sharpe ratio exceeds a benchmark given the track record's length, skewness and kurtosis (Bailey and López de Prado), and the minimum track record length needed. Takes returns or prices, or just the observed Sharpe and the number of observations.
The tool is probabilistic_sharpe_ratio 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
| Argument | Required | Type |
|---|---|---|
returns | no | number[] |
prices | no | number[] |
periods_per_year | no | number |
sharpe_annual | no | number |
observations | no | integer |
skew | no | number |
kurtosis | no | number |
benchmark_sharpe | no | number |
confidence | no | number |
How a model reaches it
Ask in plain words. The model finds probabilistic_sharpe_ratio 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": "probabilistic_sharpe_ratio",
"arguments": {}
}Words that find it
Besides its name, title and description, find_tool matches a question to probabilistic_sharpe_ratio on these words: probabilistic, sharpe, ratio, psr, probability, real, genuine, skill, significant, minimum, track, record, length, mintrl, skewness, kurtosis, confidence.
More
Nothing here is investment advice.