Different Mycobacterium spp. infections may indicate varied treatment regimens in the clinic. Thus, the species-level identification of Mycobacterium spp. is one of the most important tasks for a clinical microbiology laboratory. Although matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) has emerged as a rapid and accurate method for the identification of mycobacteria, this method lacks a comprehensive evaluation of the identification accuracy for clinically collected mycobacteria using VITEK MS Knowledge Base Version 3.0 (Ver 3.0). The objectives of the present study were to evaluate the identification performance of Mycobacterium spp. using Ver 3.0 and a sample processing kit for strain inactivation and protein extraction. Among the 507 Mycobacterium isolates, 46 isolates were M. tuberculosis, and 461 isolates were nontuberculous mycobacteria (NTM) (including 27 species: 17 species were slowly growing mycobacteria (SGM), and 10 species were rapidly growing mycobacteria (RGM)). The VITEK MS V3.0 library was used to correctly identify 476/507 (93.9%) isolates (425 isolates were correctly identified initially, and 51 more isolates were correctly identified on repeat), 23/507 (4.5%) isolates were unidentified, and 8/507 (1.6%) isolates were misidentified. In summary, we showed that Mycobacterium spp. can be adequately identified by Ver 3.0 in combination with the use of a standard sample processing kit.