A Monte Carlo program is available to generate samples from a Wright–Fisher neutral model of genetic variation. The program assumes an infinite-sites mutation model and allows recombination, gene conversion, symmetric migration, and various demographic histories. It can be used to study the statistical properties of sample statistics under these models. The program is written in C and available at http://home.uchicago.edu/~rhudson1/source/mksamples.html. It can generate samples under a variety of assumptions using a coalescent approach. The program allows recombination, gene conversion, migration under a symmetric island model, and simple population size changes. The model assumes the standard coalescent approximation to the Wright–Fisher model, which is accurate for small sample sizes relative to population size. The program generates a random genealogical history of a chromosome segment and places mutations on the genealogy according to a Poisson distribution. The mutation parameter is 4N₀u, where N₀ is the effective diploid population size and u is the mutation rate. The program can simulate samples for constant population size without subpopulations, recombination, or gene conversion by specifying sample size, number of replicate samples, and mutation parameter. For example, 'ms 5 100 -t 3.0 > outfile' generates 100 samples of 5 chromosomes with 4N₀u = 3.0. Additional command line arguments are needed for other complications like recombination, gene conversion, migration, or changing population size. The output includes the command line, seed value, and samples. Each sample begins with '//' and includes the number of polymorphic sites, their positions, and the gametes. The program is written in C and has been compiled on Linux, SunOS, and macOS. Random number generation is isolated in rand1.c and can be modified for other generators. References are provided for further reading.A Monte Carlo program is available to generate samples from a Wright–Fisher neutral model of genetic variation. The program assumes an infinite-sites mutation model and allows recombination, gene conversion, symmetric migration, and various demographic histories. It can be used to study the statistical properties of sample statistics under these models. The program is written in C and available at http://home.uchicago.edu/~rhudson1/source/mksamples.html. It can generate samples under a variety of assumptions using a coalescent approach. The program allows recombination, gene conversion, migration under a symmetric island model, and simple population size changes. The model assumes the standard coalescent approximation to the Wright–Fisher model, which is accurate for small sample sizes relative to population size. The program generates a random genealogical history of a chromosome segment and places mutations on the genealogy according to a Poisson distribution. The mutation parameter is 4N₀u, where N₀ is the effective diploid population size and u is the mutation rate. The program can simulate samples for constant population size without subpopulations, recombination, or gene conversion by specifying sample size, number of replicate samples, and mutation parameter. For example, 'ms 5 100 -t 3.0 > outfile' generates 100 samples of 5 chromosomes with 4N₀u = 3.0. Additional command line arguments are needed for other complications like recombination, gene conversion, migration, or changing population size. The output includes the command line, seed value, and samples. Each sample begins with '//' and includes the number of polymorphic sites, their positions, and the gametes. The program is written in C and has been compiled on Linux, SunOS, and macOS. Random number generation is isolated in rand1.c and can be modified for other generators. References are provided for further reading.