Learning Analytics (LA) is increasingly applied to assess and foster creativity in educational settings. Whereas existing applications have shown promise in STEM contexts, less is known about the diversity of approaches across educational domains. Therefore, we conducted a scoping review that systematically mapped LA applications for creativity in educational contexts. Searches returned 278 articles, with 41 studies meeting eligibility criteria. Analysis revealed five fundamental mechanisms through which LA fosters creativity: process visualization, adaptive feedback, automated pattern recognition, behavioural analytics, and real-time intervention. Computational creativity (10 studies) was the most prevalent conceptualization, with log data as the primary source (12 studies) and automated assessment via platform-based metrics as the leading approach (10 studies). Programming platforms represented the main technological applications (11 studies), while collaborative learning was the most common pedagogical strategy (7 studies). Problem-solving emerged as the most frequently linked complementary skill (17 studies). However, research showed extensive STEM focus; methodological fragmentation, with 38 studies lacking specified study duration; and theoretical gaps, with nine studies missing explicit theoretical frameworks. These findings highlight LA's transformative potential for creativity assessment and fostering while revealing opportunities for interdisciplinary expansion and methodological standardization.