Abstract Background Cognitive frailty is a risk for many adverse health outcomes that are commonly observed in older people. Physical activity is known to be effective to reserve cognitive frailty but the prevalence of physical inactivity is still high in older people. E-health enhances behavioural change effects through an innovative way to deliver behavioural change methods that can enhance the behavioural change effects. However, its effects on older people with cognitive frailty, its effects compared with conventional behavioural change methods, and the sustainability of the effects are unclear. Methods This study employs a single-blinded, two-parallel-group, non-inferiority, randomized controlled trial design with a 1:1 group allocation ratio. Eligible participants are aged 60 years or above, have cognitive frailty and physical inactivity, and possess a smartphone for more than six months. The study will be conducted in community settings. In the intervention group, participants will receive a 2-week brisk-walking training followed by a 12-week e-health intervention. In the control group, participants will receive a 2-week brisk-walking training followed by a 12-week conventional behavioural change intervention. The primary outcome is minutes of moderate-to-vigorous physical activity (MVPA). This study aims to recruit a total of 184 participants. Generalized estimating equations (GEE) will be used to examine the effects of the intervention. Ethics and dissemination The trial has been registered at ClinicalTrials.gov (Identifier: NCT05758740) on 7th March 2023, https://clinicaltrials.gov/ct2/show/NCT05758740, and all items come from the World Health Organization Trial Registration Data Set. It has been approved by the Research Ethics Committee of Tung Wah College, Hong Kong (reference number: REC2022136). The findings will be disseminated in peer-reviewed journals and presented at international conferences relevant to the subject fields. Trial registration The trial has been registered at ClinicalTrials.gov (Identifier: NCT05758740) and all items come from the World Health Organization Trial Registration Data Set. The latest version of the protocol was published online on 7th March 2023.