Metal cutting using flood cooling has serious impacts on the environment and operator health. Therefore, the minimum quantity lubricant (MQL) technique has been proposed as a promising alternative to the conventional flood cooling technique. Replacing mineral oils by eco-friendly vegetable oils gives another environmental advantage to MQL metal cutting. In this study, two types of nanoparticles (Al2O3 and CuO) are added to rice bran vegetable oil to obtain eco-friendly nanofluid with enhanced thermophysical properties, which utilized as a cutting fluid in the so-called MQL-turning with nano-lubricants (MQL-TNL). The experimental plan was designed according to Taguchi L16 method. The effects of the main cutting parameters such as cutting speed, cutting depth, and feed on the cutting force, surface roughness, tool wear are investigated. Among all cutting parameters, cutting speed has the highest effect on all process responses. The use of CuO/oil nanofluid as a cutting fluid produces smooth machined surfaces with little tool wear compared with that of Al2O3/oil nanofluid. Moreover, an improved random vector functional link (RVFL) model trained using experimental results is utilized to predict the responses of the cutting process. The accuracy of the model is enhanced via incorporation with a metaheuristic optimization algorithm called political optimizer (PO), which used to obtain the optimal RVFL parameters. The predicted results obtained by the developed RVFL-PO model are compared with the experimental ones as well as those obtained by standalone RVFL and hybrid RVFL-PSO (particle swarm optimization). The accuracy of the three models is assessed using various statistical measures. The RVFL-PO shows the best accuracy among others. The lowest coefficient of determination of the predicted results for all investigated cases was 0.768, 0.844, and 0.961 for RVFL, RVFL-PSO, and RVFL-PO, respectively.