A supply chain is a key definition in logistics. The supply chain is a set of logistics system nodes that is linearly ordered by the material, information or financial flow in order to analyze or synthesize a specific set of logistic functions and (or) costs. Multi-agent systems are suitable for the domains that involve interactions between different people or organizations with different (possibly conflicting) goals and proprietary information. They view the supply chain as a set of intelligent agents, each responsible for one or more activities in the supply chain. The ontology, in turn, describes the domain area and becomes a mechanism to aid in understanding and analyzing the information flow between agents. The use of ontologies for multi-agent system provides the following benefits: the ontology enables knowledge structuring and sharing, increases the reliability of agent system and provides the basis for the interaction between the agents. This paper proposes a method of multi-agent system application for supply chain node cooperation and shows the interaction between agents inside one of the supply chain nodes – manufacturer node.