ktx AI Data Agents

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, business knowledge from wikis and dbt, and a semantic layer into one searchable surface. Agents use ktx through MCP tools to fetch canonical SQL and metric logic instead of inventing queries from scratch.

What ktx Does

• Learns from company knowledge: Ingests dbt, Looker, Metabase, Notion, and wiki content; organizes and deduplicates it; flags contradictions
• Maps the data stack: Samples tables, captures metadata, detects joinable columns, resolves fan/chasm traps
• Builds a semantic layer: Combines raw tables and high-level metrics through a join graph
• Serves agents: Exposes CLI and MCP tools with full-text and semantic search across wiki and semantic entities

Works with PostgreSQL, Snowflake, BigQuery, ClickHouse, MySQL, SQL Server, SQLite.

Installation

Global CLI