We study the effect of extrinsic noise in metabolic networks. We introduce external random fluctuations at the kinetic level, and show how these lead to a stochastic generalization of standard metabolic control analysis. While summation and connectivity theorems hold true in the presence of extrinsic noise, control coefficients incorporate its effect through an explicit dependency on the noise intensity. New elasticities and response coefficients are also defined. Accordingly, the concept of control by noise is introduced as a way of tuning the systemic behaviour of metabolisms. We argue that this framework holds for intrinsic noise too, when time-scale separation is present in the system.