Smart contract vulnerabilities can cause substantial financial losses due to the immutability of code after deployment. While existing tools detect vulnerabilities, they cannot effectively repair them. In this paper, we propose SCPatcher, a framework that combines a Retrieval-Augmented Generation (RAG) with Knowledge Graph (KG) for automated smart contract repair. We construct a knowledge graph from 5,000 verified Ethereum contracts, extracting function-level relationships to build a semantic network. This graph serves as an external knowledge base that enhances Large Language Model (LLM) reasoning and enables precise vulnerability patching. We introduce a two-stage repair strategy, initial knowledge-guided repair followed by Chain-of-Thought (CoT) reasoning for complex vulnerabilities. Evaluated on 200 vulnerable contracts, SCPatcher achieves a 81.5% overall repair rate and 91.0% compilation pass rate, substantially outperforming existing methods.