canli-mcp / Factor backtests
Backtest a signal without lookahead
Backtest a signal against your prices: rank, long and short quantiles, rebalance, trading only on what was known lag_days earlier, costs on actual trades. Every reply holds the result against the crises its dates cover and lists the ones it does not. With capital_usd and dollar_volume_file, orders fill only as far as the market traded, pay square-root impact, and the reply shows the Sharpe at each size the market can take. Pass ledger to judge the best of a search against all of it. A backtest measures one path of history under these costs; it does not establish that the signal will keep working.
The tool is backtest_signal in canli-mcp 0.22.0, free and MIT-licensed, with no account and no API key. It comes from canli-backtest-mcp, which canli-mcp includes, and it is also its own server.
Arguments
| Argument | Required | Type |
|---|---|---|
prices_file | yes | string |
signal_file | yes | string |
rebalance | no | weekly|monthly|quarterly|integer |
lag_days | no | integer |
side | no | long_short|long_only |
quantile | no | number |
cost_bps | no | number |
min_names | no | integer |
periods_per_year | no | number |
capital_usd | no | number |
dollar_volume_file | no | string |
max_participation | no | number |
impact_coefficient | no | number |
crisis_drawdown_limit | no | number |
ledger | no | string |
label | no | string |
How a model reaches it
Ask in plain words. The model finds backtest_signal 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_signal",
"arguments": {
"prices_file": "<string>",
"signal_file": "<string>"
}
}Words that find it
Besides its name, title and description, find_tool matches a question to backtest_signal on these words: test, my, signal, csv, prices, backtest, without, lookahead.
More
Nothing here is investment advice.