canli-mcp / Quant finance

Backtest 52-week-high momentum

Backtest holding the assets trading closest to their trailing high (George-Hwang 52-week-high momentum), re-ranked on a schedule.

The tool is backtest_high_proximity 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[][]
windownointeger
top_fractionnonumber
rebalance_everynointeger
curvenoboolean
datesnostring[]
cost_bpsnonumber
periods_per_yearnonumber
risk_freenonumber
long_onlynoboolean

How a model reaches it

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

Words that find it

Besides its name, title and description, find_tool matches a question to backtest_high_proximity on these words: 52, week, high, momentum, proximity, george, hwang, anchoring, ranking, backtest.

More

Nothing here is investment advice.