ktx AI Data Agents Context Layer

Skill by ara.so — MCP Skills collection.

ktx is an executable context layer for data and analytics agents. It teaches AI agents (Claude Code, Codex, Cursor, etc.) how to query your data warehouse accurately by combining approved metric definitions, joinable columns, and business knowledge from your entire data stack.

What ktx Does

ktx solves the problem of general-purpose agents struggling with data tasks. Instead of re-exploring your warehouse on every question and inventing metric logic, ktx:

• Learns from company knowledge — ingests wiki content, organizes it, removes duplicates, flags contradictions
• Maps the data stack — samples tables, captures metadata, detects joinable columns, annotates sources
• Builds a semantic layer — combines raw tables and high-level metrics through a join graph that resolves chasm and fan traps
• Serves agents at execution — exposes CLI and MCP tools with semantic search across wiki and semantic-layer entities

Supported databases: PostgreSQL, Snowflake, BigQuery, ClickHouse, MySQL, SQL Server, SQLite

Integrations: dbt, MetricFlow, LookML, Looker, Metabase, Notion