ktx-data-agent-context-layer

Official

Give agents accurate data semantics

AuthorAradotso
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It solves the problem of AI agents generating incorrect or inconsistent SQL for data warehouses by grounding answers in a shared semantic layer built from your real warehouse metadata, dbt models, and business definitions.

Core Features & Use Cases

  • Automatic semantic layer creation: Builds approved metrics, dimensions, and relationships from warehouse introspection and dbt artifacts.
  • Business context + wiki integration: Connects operational definitions (wiki, dbt docs, and other sources) to resolve meaning, contradictions, and terminology.
  • MCP tool access for agents: Exposes read-only MCP tools for semantic search and wiki retrieval so agents can select canonical logic before querying.
  • Read-only guardrail: Avoids writing back to your data warehouse to reduce risk during agent usage.

Quick Start

Run ktx setup in your analytics project directory, configure your warehouse connection and context sources, ingest to build the semantic layer, then start the MCP server with ktx mcp start.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ktx-data-agent-context-layer
Download link: https://github.com/Aradotso/mcp-skills/archive/main.zip#ktx-data-agent-context-layer

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.