The annotation of small molecules is one of the most challenging and important steps in untargeted mass spectrometry analysis, as most of our biological interpretations rely on structural annotations. Molecular networking has emerged as a structured way to organize and mine data from untargeted tandem mass spectrometry (MS/MS) experiments and has been widely applied to propagate annotations. However, propagation is done through manual inspection of MS/MS spectra connected in the spectral networks and is only possible when a reference library spectrum is available. One of the alternative approaches used to annotate an unknown fragmentation mass spectrum is through the use of in silico predictions. One of the challenges of in silico annotation is the uncertainty around the correct structure among the predicted candidate lists. Here we show how molecular networking can be used to improve the accuracy of in silico predictions through propagation of structural annotations, even when there is no match to a MS/MS spectrum in spectral libraries. This is accomplished through creating a network consensus of re-ranked structural candidates using the molecular network topology and structural similarity to improve in silico annotations. The Network Annotation Propagation (NAP) tool is accessible through the GNPS web-platform https://gnps.ucsd.edu/ProteoSAFe/static/gnps-theoretical.jsp. For genome analysis it is commonly accepted that one can hypothesize the function of genes based on sequence similarity, using annotated reference sequences. Once a homology hypothesis has been made based on reference annotations, it allows one to build hypothesis in terms of function and ultimately understand the underlying biology. In contrast, mass spectrometry (MS) can detect many molecules, as ions, yet we often cannot link a MS signal to a molecule. The reference libraries to annotate fragmented molecular data only cover a small portion of the known molecular space. The use of computational (in silico) fragmentation predictions from structural libraries offers a promising alternative. One of the weaknesses of the molecular annotation using such in silico approaches is that they currently annotate the molecules individually. However, molecular relationships, based on spectral similarity, can be used to enhance the structural hypothesis inferred from the annotation of molecules detected by mass spectrometry. We introduce an online tool called “Network Annotation Propagation” that uses a combination of molecular networks, based on spectral similarity, from which we infer molecular similarity, together with in silico fragmentation, to enable the scientific community to strengthen their MS annotations.