R MCP Server

Run ANOVA (one-way or multi-way) with optional post-hoc tests.

Fit a linear mixed-effects model using lme4.

Compute bootstrap confidence intervals for a statistic.

Run multiple normality tests and produce a Q-Q plot.

Detect outliers in numeric columns of a data file.

Fit quantile regression models at specified quantiles.

Fit Kaplan-Meier survival curves with optional log-rank test.

Statically analyze R code using the lintr package.

Load a data file (CSV, TSV, or RDS) and return summary statistics.

List all installed R packages with their versions.

Return R version string, platform info, and session details.

Run k-means clustering with elbow plot and cluster visualization.

Run hierarchical clustering and produce a dendrogram.

Read data from CSV, TSV, Excel (.xlsx), JSON, or RDS files.

Execute R code that produces a data frame and save it to a file.

Reshape data between wide and long formats using tidyr.

Merge (join) two data files on common columns.

Generate or load a built-in R sample dataset and save it as CSV.

Compute probability distribution values (density, CDF, quantile, random).

Plot a probability distribution: histogram of random samples with theoretical density overlay.

Sample from a population with or without replacement (like dice, cards, lottery). The code must create a vector named `population`.

Create a Q-Q (quantile-quantile) plot to assess distributional fit.

Simulate the Central Limit Theorem for any distribution.

Create a scatterplot matrix (pairs plot) for multivariate EDA.

Create a kernel density estimation plot.

Create an empirical cumulative distribution function (ECDF) plot.

Create a stem-and-leaf display — a text-based distribution summary.

Test equality of variances between groups.

Execute inline R code and return the console output.

Execute an .R script file and return its output.

Run a testthat test file and return pass/fail results.

Create a plot using ggplot2 and save as PNG.

Generate a correlation heatmap from a data file using ggplot2.

Create a multi-panel figure from multiple ggplot objects.

Create an interactive plotly visualization saved as HTML.

Create publication-ready plots using ggpubr.

Create a correlation plot using the corrplot package.

Create a group comparison plot with statistical significance using ggpubr.

Create regression diagnostic plots (residuals, Q-Q, scale-location, leverage).

Run a proportion test (one-sample or two-sample) using prop.test.

Run an exact binomial test using binom.test.

Run a chi-squared test for goodness of fit, independence, or homogeneity.

Run Fisher's exact test on a 2x2 contingency table.

Create a contingency table with chi-squared test and mosaic plot.

Fit a robust regression model resistant to outliers.

Fit polynomial regression models of various degrees and compare.

Make predictions from a linear model with confidence and prediction intervals.

Perform Tukey's Honest Significant Difference post-hoc test after ANOVA.

Run a Kruskal-Wallis rank sum test — nonparametric alternative to one-way ANOVA.

Compute statistical power or required sample size.

Fit a linear or generalized linear model and return the summary.

Compute a correlation matrix for numeric columns in a data file.

Run a statistical hypothesis test and return structured results.

Compute detailed descriptive statistics for a data file.

Run Principal Component Analysis on numeric columns of a data file.

Fit a time series model and produce a forecast with plot.

Decompose a time series into trend, seasonal, and remainder.

Test a time series for stationarity (unit root).

Plot the ACF and PACF of a time series side by side.

Execute R plotting code and save the result as a PNG file.

Render an R Markdown (.Rmd) file to HTML or PDF.

Install an R package from CRAN.