Corbat MCP is an AI coding standards server that injects team coding specifications before the AI generates code through the MCP protocol, ensuring that the generated code meets production standards, security requirements, and passes the code review. It supports multiple programming languages and development tools.

Sandbox MCP is a model context protocol server that allows LLMs to run code in secure Docker containers, solving the security problem of the inability to test code generated by AI.

Rigour is an AI code agent governance platform that provides real-time security scanning, quality gates, and memory governance to prevent sensitive information leakage and ensure the quality of code generated by AI.

Moonbridge is an MCP server that allows multiple AI coding agents (supporting backends such as Kimi, Codex, OpenCode, Gemini) to be generated in parallel from MCP clients such as Claude Code and Cursor, used to try multiple code solutions simultaneously, enabling parallel exploration and task execution at a lower cost.

A restaurant reservation system based on Spring Boot and Spring AI, developed using an API-first approach, integrating client code generated by OpenAPI and AI chatbot functionality, and supporting multiple LLM service providers.