# SLayer

> MIT embeddable semantic layer for agents — MCP, SQL expressions, dbt/Cube import

**Category:** AI Agents  
**Pricing:** open-source  
**URL:** https://motley.ai/slayer  
**GitHub:** https://github.com/MotleyAI/slayer  
**Added:** 2026-09-19

---

## The Hook

SLayer is a semantic layer built for agent search→inspect→query — define metrics once, ask with expressions, expose MCP/REST/CLI/Flight SQL without forcing classic BI pre-aggregations.

## What's Good

MIT (MotleyAI/slayer). uv-installable Python library and standalone tool with MCP, REST, CLI, Flight SQL, and a Postgres-shaped SQL facade. Expression queries (sum/avg/ratios/time_shift) plus memory/search for business context. Imports dbt, Cube, and Ossie configs so you can sit beside an existing warehouse stack instead of replacing it.

## The Catch

Vs warehouse/BI tools and raw SQL MCP: SLayer is the metric/expression layer agents query, not a database or a full BI product. You still own warehouse credentials, row-level security design, and whether definitions stay truthful. Young Motley surface — verify connectors for your engine before betting a production agent on it.

## Verdict

OSS semantic layer for agentic analytics. Expressions + MCP over your warehouse; not another vector RAG pack.