You'd reach for this when you need to run statistical association tests on categorical data without switching to R or a Jupyter notebook. It exposes crosstab analysis operations including chi-square tests, Fisher's exact test for small samples, odds ratios, and effect size calculations. The implementation appears lightweight based on the crosstabs-lite source package. Useful for quick exploratory analysis when you're working with survey data, A/B test results, or any scenario where you need to test whether two categorical variables are independent. Saves you from context switching to a statistical computing environment for common contingency table operations.
claude mcp add --transport stdio io.github.barangaroo-crosstabs-mcp -- uvx crosstabs-mcp