The underlying source of climate variability affecting the Ceará rain-fed agricultural production in Northeast Brazil is the interrelated global-scale fluctuations of sea-surface temperature (SST) in the tropical Pacific and Atlantic regions. Despite the elevated skill in seasonal climate forecasts for rainfall in Ceará, models linking SST anomalies (SSTAs) in the tropical Pacific (Niño 3.4 index) and Atlantic (Dipole index) regions to crop production are not well developed. The results of this study show that clear connections among episodes of drought patterns and maize and bean production and yields over the rainy season result from seasonally changing SSTAs. Total seasonal maize and bean production are inversely correlated with Niño 3.4 and Atlantic Dipole indices, while maize and bean yields are directly correlated with Niño 3.4 and Atlantic Dipole indices but inversely correlated with maize and bean yields averaged from February to April. Year-to-year averaged February–April SSTA fluctuations explain about half the interannual variability in maize and bean production over the rainy season. There were two fluctuation shifts (from 1974 to 1981 and from 1984 to 1997, with a transition during 1982–1983) of the maize and crop production and yields that were largely in-phase with seasonal SSTAs. However, the magnitude and duration of extreme El Niño-Southern Oscillation (ENSO) and Atlantic Dipole effects on Ceará crop production and yields indicated by the vulnerability index offers some strong policy warnings.