Urban residents have a higher risk of hypertension and psychological stress than rural residents. Aside from medical interventions, understanding how to control hypertension and alleviate the stress of urban populations has become a public concern. As an alternative medical measure, forest therapy has shown the effects of normalizing blood pressure (BP) and reducing stress increasingly in recent literature, but this is still inconclusive. In order to systematically verify forest therapy's effects on the BP and mental stress of urban residents, we conducted meta-analyses to assess the changes in systolic blood pressure (SBP), diastolic blood pressure (DBP), and salivary cortisol concentration (SCC; a stress biomarker) between the forest therapy group and urban control group. We searched 4 online databases, and 21 studies on BP involving 2270 participants and 13 studies on SCC involving 1786 participants were included. Through the meta-analysis, the mean difference and confidence interval (CI) estimates indicated that forest therapy significantly reduced participants' SBP -3.44 (95% CI -5.74, -1.14), DBP -3.07 (95% CI -5.59, -0.54), and SCC -0.07 (95% CI -0.10, -0.04), as compared with urban control. Yet, there was substantial heterogeneity (I-2 = 72.87-88.59%) among these studies. We also found that each prediction interval (PI) for SBP (95% PI -13.30, 6.42), DBP (95% PI -15.54, 9.41), and SCC (95% PI -0.18, 0.05) were all much wider than the CIs and contained values above 0. This means that forest therapy may reduce SBP, DBP, and SCC on average, but may not exclude adverse results. Meta-regression analyses showed that participants' age and baseline SBP levels determined the heterogeneity among SBP studies. After forest therapy, older participants and those with higher baseline SBP levels had greater SBP-lowering effects. Among DBP studies, the primary source of heterogeneity was participants' baseline DBP levels; participants with higher baseline DBP levels had greater DBP reduction. In subgroup analyses, we discovered that longer-term forest therapy programs (>= 20 min) resulted in a greater reduction in BP and SCC than shorter-term forest therapy programs (<20 min). Additionally, seated viewing, walking, or multi-session programs in forests were observed to have similar effects on reducing BP and SCC. Despite extensive analyses, the study did not identify any sources of heterogeneity among forest therapy programs for lowering SCC levels. Overall, we conclude that forest therapy programs have beneficial therapeutic effects on urban residents' physio-psychological health through lowering BP and relieving stress (reducing SCC). This finding provides solid evidence of the contribution of forest therapy to urban residents' health and wellbeing.