We study the optimal mechanism design problem faced by a market intermediary who makes revenue by connecting buyers and sellers. We first show that the optimal intermediation protocol has substantial structure: it is the solution to an algorithmic pricing problem in which seller's costs are replaced with virtual costs, and the sellers' payments need only depend on the buyer's behavior and not the buyer's actual valuation function. Since the underlying algorithmic pricing problem may be difficult to solve optimally, we study specific models of buyer behavior and give mechanisms with provable approximation guarantees. We show that offering only the single most profitable item for sale guarantees an fraction of the optimal revenue when item value distributions are independent and have monotone hazard rates. We also give constant factor approximations when the buyer considers all items at once, items at once, or items in sequence.