Paparats is a self-hosted Model Context Protocol (MCP) server that gives AI coding agents and assistants a deep, semantically-indexed understanding of local codebases. It indexes multiple repositories with AST-aware chunking, semantic search, cross-repository symbol tracing, and a persistent architectural knowledge base. Targeted at developers, teams, and anyone building smart agents, Paparats ensures context-aware coding help, efficient onboarding, and consistent knowledge across large or legacy codebases—all from a single, privacy-respecting, local solution.
Visit Paparats's official website for product details and getting started.
Comprehensive guide on how to set up and use Paparats, including API references and configuration details.
Explore various use cases and examples of how to implement Paparats in different scenarios.