canli-mcp / Quant finance
Cluster sleeves by behavior
Group the sleeves that ran on your prices by return correlation (average linkage on sqrt((1 - rho) / 2)), to see how many genuinely different bets the library makes on this data and the best sleeve of each group.
The tool is sleeve_clusters 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 |
|---|---|---|
prices | yes | number[]|number[][] |
cost_bps | no | number |
periods_per_year | no | number |
risk_free | no | number |
asset | no | integer |
pair | no | any[] |
symbols | no | string[] |
families | no | (ma_crossover|time_series_momentum|trend_ensemble|breakout|...)[] |
ids | no | string[] |
min_evaluation | no | integer |
threshold | no | number |
How a model reaches it
Ask in plain words. The model finds sleeve_clusters 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": "sleeve_clusters",
"arguments": {
"prices": "<number[]|number[][]>"
}
}Words that find it
Besides its name, title and description, find_tool matches a question to sleeve_clusters on these words: sleeve, clusters, correlation, hierarchical, clustering, redundancy, distinct, strategies, effective, number, diversification.
More
Nothing here is investment advice.