A new clustering algorithm, based on Adaptive Local Density (ALD) and Evidential K-Nearest Neighbors (EKNN), is proposed here. In density peaks clustering, many other density metrics fail to detect cluster centers on multi-density datasets, however the ALD deals with the tasks very well since it can better utilize the local information. To assign the remaining points after detecting the cluster centers, an assigning strategy in the framework of evidential theory, named EKNN, is created. The advantage of EKNN is twofold. Firstly, by fusing the information of K-Nearest Neighbors, it can reduce the risk of a phenomenon named domino effect: the drawback of one classical clustering, i.e., clustering by fast search and find of density peaks (always named as DPC). Secondly, it can detect border and noise points simultaneously since a credal partition is derived which can mine ambiguity and uncertainty of data structure. Simulations on both synthetic and real-world datasets demonstrate the outstanding performance of ALD-EKNN compared with DPC and some of its successors.