Abstract Background Delirium is a syndrome characterized by acute fluctuations and alterations in attention and arousal. Critically ill patients are at particularly high risk, and those that develop delirium are more likely to experience poor clinical outcomes such as prolonged duration of ICU and hospital length of stay, and increased mortality. Melatonin and melatonin agonists (MMA) have the potential to decrease the incidence and severity of delirium through their hypnotic and sedative-sparing effects, thus improving health-related outcomes. The objective of this review is to synthesize the available evidence pertaining to the efficacy and safety of MMA for the prevention and treatment of ICU delirium. Methods We will search Ovid MEDLINE, Web of Science, EMBASE, PsycINFO, the Cochrane Central Register of Controlled Trials (CENTRAL), and CINAHL to identify studies evaluating MMA in critically ill populations. We will also search http://apps.who.int/trialsearch for ongoing and unpublished studies and PROSPERO for registered reviews. We will not impose restrictions on language, date, or journal of publication. Authors will independently screen for eligible studies using pre-defined criteria; data extraction from eligible studies will be performed in duplicate. The Cochrane Risk of Bias Scale and the Newcastle-Ottawa Scale will be used to assess the risk of bias and quality of randomized and non-randomized studies, respectively. Our primary outcome of interest is delirium incidence, and secondary outcomes include duration of delirium, number of delirium- and coma-free days, use of physical and chemical (e.g., antipsychotics or benzodiazepines) restraints, duration of mechanical ventilation, ICU and hospital length of stay, mortality, long-term neurocognitive outcomes, hospital discharge disposition, and adverse events. We will use Review Manager (RevMan) to pool effect estimates from included studies. We will present results as relative risks with 95% confidence intervals for dichotomous outcomes and as mean differences, or standardized mean differences, for continuous outcomes. Discussion Current guidelines make no pharmacological recommendations for either the prevention or treatment of ICU delirium. This systematic review will synthesize the available evidence on the efficacy and safety of MMA for this purpose, thus potentially informing clinical decision-making and improving patient outcomes. Systematic review registration PROSPERO CRD42015024713