canli-mcp / Quant finance

Index tracking portfolio

Find long-only weights in a subset of assets that minimize ex-ante tracking error to a benchmark's weights, with an optional per-asset cap.

The tool is index_tracking_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[]
benchmark_weightsyesnumber[]
allowednoboolean[]
max_weightnonumber

How a model reaches it

Ask in plain words. The model finds index_tracking_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": "index_tracking_portfolio",
  "arguments": {
    "benchmark_weights": "<number[]>"
  }
}

Words that find it

Besides its name, title and description, find_tool matches a question to index_tracking_portfolio on these words: index, tracking, replication, error, minimization, benchmark, subset, sampling, optimizer.

More

Nothing here is investment advice.