We develop and test a source mechanism analysis similar to the source‐scanning approach (SSA) that automatically outputs the most likely source mechanism and associated probability density function. Our analysis is based on the polarity of the first period of each body wave observed at all stations, but does not require polarity picking. We find the first period using a manually picked arrival time and measure the central period of the signal power using the second moment of the power spectral density function. For a given source mechanism from the predefined range of trial mechanisms, we multiply the first period of each body wave by its corresponding theoretical polarity and stack the signals from all of the observing stations. As in other SSAs, our method is not based on the optimization of an objective function through an inversion. Instead, the power of the polarity‐corrected stack is a proxy for the likelihood of the trial source mechanism, with the most powerful stack corresponding to the most likely source mechanism. Using synthetic data, we test our method for robustness to the data coverage, its azimuthal gap, the signal‐to‐noise ratio (SNR), the travel‐time picking error, and non‐double‐couple components. Then, we present results for field data in volcano‐tectonic and tectonic contexts. Our results are reliable when constrained by 15 body wavelets with a gap less than 150°, SNR of over 1, and an arrival‐time error of less than one‐fifth of the period of the body wave. We demonstrate the use of the SSA for source mechanism analysis with similar advantages to waveform inversion (no manual polarity picking and probabilistic approach) and similar applicability to polarity inversion (any source size and any instrument type).