Lack of access to credit prevents poor households in developing countries from diversifying into income‐generating activities that could safeguard them against unforeseen shocks and seasonality, leaving them susceptible to food deprivation, even when aggregate food supplies are adequate. Microcredit programmes help these households to access financial capital that could help improve their food security situation. We examine how microcredit affects different measures of food security; namely, household calorie availability, dietary diversity indicators and anthropometric status of women of reproductive age (15–49 years) and children under the age of 5 years. We find that microcredit programme participation increases calorie availability both at the intensive and extensive margins, but does not improve dietary diversity and only has mixed effects on the anthropometric measures. We also find that the effect of microcredit participation on food security may be non‐linear in which participation initially has either no effect on food security or may actually worsen it, before improving it in the longer run. Our results help to explain why existing short‐term evaluations of microcredit sometimes do not show any positive effects.