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.
Deterministic slop detector for AI-generated prose. Flags filler phrases and clichés with zero false positives by design (curated phrase list, not a model), returns exact spans plus a pinnable 0-1 score, and runs offline with no API key. CLI + CI exit code + MCP server for agents to self-check their own output before it lands in a PR or doc. pip install defluff
Semantic code index that extracts domain concepts, naming conventions, and behavioral similarity from codebases. One tool call instead of 19, 20x fewer tokens for codebase understanding queries.