Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
Local repo-intelligence index and MCP server for coding agents — "what a repository knows about itself." Hybrid BM25 + vector semantic search, a tree-sitter code graph (callers/callees/imports across Rust, TS/TSX, Kotlin, C/C++, Python) with an optional compiler-grade SCIP oracle, queryable git/GitHub history, and typed, source-anchored repo memories (Invariant, Decision, Risk, …) that persist across sessions. Every result carries provenance — confidence labels and coverage warnings. Keeps source read-only; a background watcher keeps queries fresh. PreToolUse hooks augment grep and flag near-duplicate code as you write it. cargo install rag-rat
Local-first codebase intelligence engine. Gives coding agents structured context packets, indexed code/schema facts, and diagnostics over MCP, backed by a local SQLite store — so agents stop rediscovering your repo with raw grep. Optional Postgres/Supabase awareness and a bundled Claude Code plugin.