This paper provides evidence consistent with elite capture of Social Fund investment projects in Ecuador. Exploiting a unique combination of data sets on village-level income distributions, Social Fund project administration, and province-level electoral results, we test a simple model of project choice when local political power is unequally distributed. In accordance with the predictions of the model, poorer villages are more likely to receive projects that provide excludable (private) goods to the poor, such as latrines. Controlling for poverty, more unequal communities are less likely to receive such projects. Consistent with the hypothesis of elite capture, these results are sensitive to the specific measures of inequality and elite power used in the empirical analysis, and are strongest for expenditure shares at the top of the distribution.