To improve the early recognition of danger signs in children with severe febrile illness in low resource settings, WHO promotes automated respiratory rate (RR) counting, but its performance is unknown in this population. Therefore, we prospectively evaluated the field performance of automated point-of-care plethysmography-based RR counting in hospitalized children with severe febrile illness (<5 years) in DR Congo. A trained research nurse simultaneously counted the RR manually (comparative method) and automatically with the Masimo Rad G pulse oximeter. Valid paired RR measurements were obtained in 202 (83.1%) children, among whom 43.1% (87/202) had fast breathing according to WHO criteria based on manual counting. Automated counting frequently underestimated the RR (median difference of −1 breath/minute; p2.5–p97.5 limits of agreement: −34–6), particularly at higher RR. This resulted in a failure to detect fast breathing in 24.1% (21/87) of fast breathing children (positive percent agreement: 75.9%), which was not explained by clinical characteristics (p > 0.05). Children without fast breathing were mostly correctly classified (negative percent agreement: 98.3%). In conclusion, in the present setting the automated RR counter performed insufficiently to facilitate the early recognition of danger signs in children with severe febrile illness, given wide limits of agreement and a too low positive percent agreement.