This paper presents modular self-reconfigurable robots for grasping an unknown object based on a grasp quality metric. The presented self-reconfiguration approach makes use of basic motions performed by individual robots to change the structure. The method to solve for forward kinematics as well as configuration representation is proposed based on relationship between robotic modules. This method can be used to update the estimated contact points in self-reconfiguration. Incorporating a grasp quality metric of form closure into self-reconfiguration, the structure for grasping can be evaluated until a desired metric is obtained. Grasping and self-reconfiguration simulation experiments are presented, showing the availability and effectiveness of the proposed approach.