We will present a cyber defense tool, CyRAG, which brings together structured data from common vulnerabilities and exposures (CVE), common weakness enumeration (CWE), CAPEC (Common Attack Pattern Enumeration and Classification), and ATT&CK (Adversarial Tactics, Techniques, and Common Knowledge) to generate accurate and context-rich responses from a large language model using retrieval augmentation technique. CyRAG employs Neo4j knowledge graphs to store and retrieve interconnected information in cybersecurity threat intelligence, enabling informed decisions and optimized cyber defense.