Semantic Context

Provides semantic code search across large codebases using ChromaDB vector storage and configurable embeddings, enabling indexing of local project directories with 50+ file type support and retrieval of code snippets with metadata tracking for development teams building knowledge bases and code navigation systems.

This semantic code search MCP server by Damian Pramparo provides enterprise-grade vector database integration for indexing and searching codebases using ChromaDB for storage and either OpenAI or Ollama for embeddings. Built with TypeScript and featuring both stdio and HTTP server modes, it offers tools for indexing local project directories with configurable file patterns, performing semantic code searches across indexed repositories, and retrieving file contents with metadata tracking including project names, file types, and chunk indexing. The implementation includes Docker Compose setup with ChromaDB, Ollama, Redis, and PostgreSQL services, comprehensive file type support covering 50+ programming languages and formats, and streaming file processing for handling large codebases efficiently, making it ideal for development teams building AI-powered code search systems, enterprise knowledge bases, and developer productivity tools that need to understand and navigate large codebases semantically.