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

As the server declares them
ArgumentRequiredType
pricesyesnumber[]|number[][]
cost_bpsnonumber
periods_per_yearnonumber
risk_freenonumber
assetnointeger
pairnoany[]
symbolsnostring[]
familiesno(ma_crossover|time_series_momentum|trend_ensemble|breakout|...)[]
idsnostring[]
min_evaluationnointeger
trainnointeger
refitnointeger
top_knointeger
benchmarknobuy_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.