ktx AI Data Agents MCP Context Skills

Skill by ara.so — MCP Skills collection.

ktx is a self-improving context layer that teaches AI agents how to query your data warehouse accurately. It combines approved metric definitions, joinable columns, wiki knowledge, and semantic layer modeling to give agents like Claude Code, Codex, and Cursor a unified understanding of your data stack.

What ktx Does

• Learns from company knowledge: Ingests wiki content (Notion, Confluence), organizes it, removes duplicates, flags contradictions
• Maps the data stack: Samples tables, captures metadata, detects joinable columns, annotates sources
• Builds semantic layer: Combines raw tables and metrics through a join graph that resolves chasm and fan traps
• Serves agents: Exposes CLI and MCP tools with full-text and semantic search across all context

Installation

Global Installation