This study demonstrates that a noninvasive brain–computer interface (BCI) using scalp-recorded electroencephalographic (EEG) activity and an adaptive algorithm can provide humans, including those with spinal cord injuries, with multidimensional point-to-point movement control comparable to that achieved with invasive BCIs in monkeys. The BCI system uses sensorimotor rhythms recorded from the scalp to control a cursor's movement in two dimensions. The adaptive algorithm optimizes the translation of EEG signals into cursor movements by adjusting weights based on past trials, focusing on the user's best-controlled EEG features. The results show that users can achieve high precision and accuracy in moving the cursor to targets, with movement times and hit rates similar to those of invasive BCIs. The study also confirms that EEG-based control does not rely on covert muscle contractions, suggesting its potential for paralyzed individuals. These findings suggest that noninvasive BCIs could be a viable option for controlling robotic arms or neuroprostheses without the need for brain implants.This study demonstrates that a noninvasive brain–computer interface (BCI) using scalp-recorded electroencephalographic (EEG) activity and an adaptive algorithm can provide humans, including those with spinal cord injuries, with multidimensional point-to-point movement control comparable to that achieved with invasive BCIs in monkeys. The BCI system uses sensorimotor rhythms recorded from the scalp to control a cursor's movement in two dimensions. The adaptive algorithm optimizes the translation of EEG signals into cursor movements by adjusting weights based on past trials, focusing on the user's best-controlled EEG features. The results show that users can achieve high precision and accuracy in moving the cursor to targets, with movement times and hit rates similar to those of invasive BCIs. The study also confirms that EEG-based control does not rely on covert muscle contractions, suggesting its potential for paralyzed individuals. These findings suggest that noninvasive BCIs could be a viable option for controlling robotic arms or neuroprostheses without the need for brain implants.