RagCode MCP
Privacy-first MCP server for semantic code search and AI-ready repositories
Visit doitmagic.github.io ↗What is RagCode MCP?
RagCode MCP is a Model Context Protocol server that indexes codebases for semantic search, enabling AI assistants like Cursor, Windsurf, GitHub Copilot, and Claude to understand entire projects through vector search and retrieval-augmented generation. It supports Go, PHP, Laravel, WordPress, JavaScript, TypeScript, React, and Python with deep abstract syntax tree analysis.
The tool runs entirely locally using Ollama for language models and Qdrant for vector storage, ensuring code privacy. Installation is streamlined to a single command with Docker, and the server provides nine tools for indexing, searching, and analyzing code across multiple platforms.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered RagCode MCP automatically. Evidence: GitHub doITmagic/rag-code-mcp; repo has .cursorrules, .windsurfrules, .github/copilot-instructions.md. View source.
Similar vibe-coded apps
TypeScript framework for building AI agents without library dependencies
In-browser behavior tree execution engine for AI agents at ~60Hz
AI code quality gate that detects and auto-fixes issues in AI-generated code
Local plugin that makes AI coding agents provide evidence and resist flattery
Local context engine that prepares task-focused file packs for AI coding agents
Cut your AI coding agent's token bill by half with terse output and compression