CodeFlow

Provides semantic code analysis and search capabilities for Python codebases through AST extraction, call graph generation, and vector embeddings, enabling rapid semantic search, architectural documentation generation, and efficient navigation of large Python projects.

This CodeFlow MCP server provides semantic code analysis and search capabilities for Python codebases through AST extraction, call graph generation, and vector embeddings via ChromaDB and sentence-transformers. Built with cognitive load optimization principles, it extracts rich metadata including cyclomatic complexity, decorators, exception handling patterns, and external dependencies, then builds persistent vector stores for rapid semantic search and call graph visualization through Mermaid diagrams with LLM-optimized output modes. The implementation features real-time file watching for incremental updates, entry point detection using multiple heuristics, and comprehensive tools for function metadata retrieval, making it valuable for developers and AI assistants who need to understand complex codebases, perform semantic code search, generate architectural documentation, and navigate large Python projects efficiently.