How to cluster areas from a similarity matrix after applying MDS (multidimentional scaling)?

I have a similarity matrix [0, 1] and I have applied MDS using:

from sklearn.manifold import MDS
model = MDS(dissimilarity='precomputed', random_state=10)
distance_df_2d = model.fit_transform(distance_df)

I got an array like this:

array([[ 0.15501518, -0.186345  ],
       [ 0.27451184,  0.28893935],
       [-0.0331501 , -0.39103297],
       [-0.17210952,  0.22422369],
       [-0.22721444, -0.47819939]])

What is the best clustering method to now verify areas from the similarity heatmap?