canli-mcp / Quant finance

Backtest a trend-filtered allocation

Backtest tactical asset allocation where each asset is held only while above its moving average (Faber-style), equal or inverse-volatility weighted.

The tool is backtest_trend_filter_allocation 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[][]
smanointeger
rebalance_everynointeger
weightingnoequal|inverse_vol
vol_lookbacknointeger
curvenoboolean
datesnostring[]
cost_bpsnonumber
periods_per_yearnonumber
risk_freenonumber
long_onlynoboolean

How a model reaches it

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

Words that find it

Besides its name, title and description, find_tool matches a question to backtest_trend_filter_allocation on these words: tactical, asset, allocation, trend, filter, moving, average, faber, gtaa, timing, backtest.

More

Nothing here is investment advice.