canli-mcp / Quant finance

Principal components of returns

Run principal component analysis on asset returns (correlation or covariance): explained variance per component, cumulative share and each component's loadings.

The tool is pca_factors 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
returnsyesnumber[][]
use_covariancenoboolean
componentsnointeger

How a model reaches it

Ask in plain words. The model finds pca_factors 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": "pca_factors",
  "arguments": {
    "returns": "<number[][]>"
  }
}

Words that find it

Besides its name, title and description, find_tool matches a question to pca_factors on these words: pca, principal, component, analysis, factors, eigenvalues, explained, variance, loadings, statistical, factor, model.

More

Nothing here is investment advice.