Hybrid Brain–Computer Interfaces (h-BCIs) for upper limb motor rehabilitation after stroke should enable the reinforcement of “more normal” brain and muscular activity. Here, we propose a noninvasive BCI-controlled Functional Electrical Stimulation (FES) device (RECOM) based on online detection of cortico-muscular activation. A pseudo-online analysis was performed on 12 stroke patients to test the ability of this hybrid feature to classify movements in real-time and to identify the best parameters to use in the online computation. Promising performances were achieved in the discrimination of movements of both the affected and unaffected hand from rest condition and show the potential of a connectivity-based h-BCI to control FES to support post-stroke motor rehabilitation.