OBJECTIVES: Network meta-analyses (NMA) are the gold standard method for comparing therapies with each other in the absence of head-to-head trials or to rank treatments based on efficacy and safety. Obtaining the data for the NMA is time consuming and NMA implementation is often repetitive. In recognition of this, a tool was developed to automate NMAs on up-to-date study data from ClinicalTrials.gov. METHODS: The tool was built as a web interface using R and Shiny.  The user decides which interventions and/or drug types to include; data from ClinicalTrials.gov is retrieved using the Sherlock® interface. An algorithm assesses and reports statistics on network connectivity and heterogeneity. NMA calculations on reasons for drug discontinuations (binary outcomes) are run in a Bayesian model with a choice of random- or fixed-effects using JAGS and default prior parameter distributions. Results are displayed next to the network diagram as a table of pair-wise comparisons of interventions and a series of diagnostics. RESULTS: Automatic NMAs could be performed with the tool in a few minutes on two case examples: all anti-depressants studies (NMA for one drug type), and all schizophrenia studies (NMA for all interventions within a given  indication). Separate results were generated for each disjointed network. CONCLUSIONS: The tool enabled to generate up-to-date NMA reports on data from ClinicalTrials.gov, while providing the user with flexibility to change default choices of interventions and conditions to include, model structure in light of the displayed network, results and diagnostics.   REFERENCES: 1. Cepeda MS, Lobanov V, Berlin JA From ClinicalTrials.gov trial registry to an analysis-ready database of clinical trial results. Clinical trials (London, England) 2013;10:347-8. 2. Cepeda MS, Lobanov V, Berlin JA Using Sherlock and ClinicalTrials.gov data to understand nocebo effects and adverse event dropout rates in the placebo arm. J Pain 2013;14:999.