Among the sources which the Laser Interferometer Space Antenna (LISA) will observe are the signals from Massive Black Hole Binaries during their inspiral, merger and ring-down phases. To estimate physical parameters of these systems and their localisations, one has to perform some form of Bayesian Inference. The most common approach to do it is through defining a likelihood function and producing posterior samples with some form of sampling technique. The disadvantage of such sampling methods is that they are slow. We propose a Bayesian parameter estimation method based on Normalising Flows, a technique which allows to make an extremely fast mapping from the base sample distribution to the posterior, conditioned on the data. This is implemented by learning this mapping in advance on the training data set and then applying the trained map to the real data. We apply this method to the data from the first LISA Data Challenge (LDC) in order to evaluate how the estimated posteriors agree with the standard approaches. The main purpose of this fast parameter estimation is to use it for multi-messenger observations and to be able to alert other observatories to perform follow-ups.