To identify patterns of structural networks associated with cognitive phenotypes detected with robotic technology in patients with temporal lobe epilepsy (TLE). Network analysis was performed using multimodal MRI from TLE patients (n=22) and healthy subjects (n=20). Five tests with the Kinarm robot were used to evaluate five cognitive domains. Four graph theory metrics were computed to characterize structural networks. Structural and cognitive phenotypes were identified using an unsupervised learning algorithm, and the association between them evaluated. Three cognitive clusters were identified from the robotic evaluation, while two clusters were identified for topological network property. Among these cognitive subgroups, 52% of patients showed no significant differences compared to controls in any of the tests studied (Cluster 1). 21 % of patients exhibited partial impairments (Cluster 2), while 27 % of patients displayed impairment in all cognitive domains (Cluster 3). The first structural cluster was similar to controls and was composed of more than 60% of patients without cognitive impairment for each of the properties studied. The second structural cluster, composed mainly of patients with impairment of three or more cognitive tests, was characterized by high transitivity and modularity and lower efficiency compared to controls. The association between cognitive and structural network clusters was significant (p = 0.039). The topological pattern of the structural network associated with a specific cognitive phenotype in patients with TLE supports the relationship between neuropsychological abnormalities and the alteration of the brain network organization. The cognitive profiles identified are consistent with those reported based on pen-and-paper screening.