canli-mcp / Quant finance

Multi-asset Kelly weights

Compute growth-optimal (Kelly) weights across assets, inverse covariance times excess returns, with half-Kelly and the implied leverage and growth rate.

The tool is kelly_portfolio 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
returnsnonumber[][]
covariancenonumber[][]
expected_returnsnonumber[]
periods_per_yearnonumber
assetsnostring[]
risk_freenonumber
fractionnonumber

How a model reaches it

Ask in plain words. The model finds kelly_portfolio 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": "kelly_portfolio",
  "arguments": {}
}

Words that find it

Besides its name, title and description, find_tool matches a question to kelly_portfolio on these words: kelly, criterion, multi, asset, growth, optimal, portfolio, leverage, half.

More

Nothing here is investment advice.