canli-mcp / The desk, built into canli-mcp
Run a hub sleeve on your prices
Backtest a sleeve from the hub, or your own in its format, on your prices through the same recipe code as every other backtest here. No contributor's code runs. The result carries the sleeve's hash and reminds you to count the trials.
The tool is hub_run in canli-mcp 0.22.0, free and MIT-licensed, with no account and no API key. It is part of canli-mcp itself, so it is there as soon as canli-mcp is added.
Arguments
| Argument | Required | Type |
|---|---|---|
id | no | string |
spec | no | object |
prices | yes | array |
periods_per_year | no | number |
cost_bps | no | number |
How a model reaches it
Ask in plain words. The model finds hub_run 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": "hub_run",
"arguments": {
"prices": "<array>"
}
}Words that find it
Besides its name, title and description, find_tool matches a question to hub_run on these words: hub, run, sleeve, backtest, community, strategy, on, my, data.
More
Nothing here is investment advice.