Information processed in a distributed cluster is shared among a cluster of distributed tasks or users by the virtue of message passing protocols (e.g., Message Passing Interface MPI) or confidential data transmitted to and from cluster computing nodes. In a public network, when a number of clusters connected to each other is increased becomes a potential threat to security applications running on the clusters. To deal with this, a Message Passing Interface (MPI) is developed to preserve security services in an unsecured network. The proposed work focuses on MPI rather than other protocols because MPI is one of the most popular communication protocols on distributed clusters. Generally AES algorithm is used for encryption/decryption and interpolation polynomial algorithm is used for key management. But, in this research work, Twisted Edwards-Form Elliptic Curve Cryptography is used. This Twisted Edwards-Form Elliptic Curve Cryptography is integrated with Message Passing Interface Chameleon version 2 (MPICH2) with standard MPI interface that becomes ESMPICH2. This approach provides better security with less overhead and fast when compared with the existing techniques. Keywords: Twisted Edwards-Form Elliptic Curve Cryptography, cluster, Message Passing Interface, High Performance.