canli-mcp / Quant finance
Walk-forward sleeve selection
Test the selection process itself: at each refit pick the top sleeves by trailing Sharpe, hold them for the next window, repeat. Compares the out-of-sample result with what the picks showed in sample, with holding every sleeve, and with the benchmark.
The tool is sleeve_walk_forward 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 |
train | no | integer |
refit | no | integer |
top_k | no | integer |
benchmark | no | buy_and_hold|cash |
How a model reaches it
Ask in plain words. The model finds sleeve_walk_forward 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_walk_forward",
"arguments": {
"prices": "<number[]|number[][]>"
}
}Words that find it
Besides its name, title and description, find_tool matches a question to sleeve_walk_forward on these words: walk, forward, out, of, sample, selection, sleeve, rotation, decay, in, vs, strategy.
More
Nothing here is investment advice.