Abstract: Catalytic hydrogenation of dicyclopentadiene (DCPD) to tetrahydrodicyclopentadiene (THDCPD), a key precursor of the high-performance aviation fuel JP-10, has attracted increasing attention in the field of high-energy-density fuels. Owing to their tunable porous structures, tailorable active sites, and flexible compositions, metal–organic frameworks (MOFs) provide promising platforms for efficient DCPD hydrogenation, but their performance must be evaluated with explicit product definitions. This Review summarizes recent advances in pristine MOFs, supported MOFs composites, and MOF-derived catalysts, with emphasis on defect engineering, frustrated Lewis pairs (FLPs), metal–support interactions, and active-site microenvironment regulation. The relationships among framework topology, electronic structure, hydrogen activation, and catalytic performance are critically discussed. In addition, recent developments in computationally driven catalyst design are comprehensively reviewed, including descriptor-guided screening, density functional theory (DFT)-assisted mechanistic analyses, and topology-dependent electronic-structure regulation. Importantly, this Review further highlights the emerging role of artificial intelligence (AI) in MOF research. Finally, machine-learning-assisted optimization, retrieval-grounded language-model planning, and human-in-the-loop closed-loop workflows are discussed as emerging tools that may support data-guided MOF synthesis and catalyst optimization, rather than as mature autonomous discovery platforms. Current challenges and future perspectives for efficient, selective and verifiable DCPD hydrogenation over MOF-based catalysts are presented.