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.
Structure any document, query it like a database. Open-source extraction engine that turns any document into typed, schema-defined records, queryable in natural language from Claude, ChatGPT, Gemini, or any MCP client.
Decompose text into classified semantic units with authority, risk, attention scores, and entity extraction. No LLM. Deterministic. Works as MCP server or CLI.