Show HN: Safety layer between AI agents and databases

Category: security

Tags: ai-safety, database-security, mcp-server

Score: 7.3/10 (Innovation: 6, Technical: 8, Documentation: 8, Utility: 7)

faz provides a safety pipeline between AI agents and databases, inspecting every query through RBAC, AST analysis, injection detection, and guardrails before execution. It supports 14 databases, integrates via MCP or REST, and offers federated queries across databases. Interesting because it fills a critical security gap as LLM agents gain more autonomous database access.

Target audience: backend devs, devops, data engineers

Repository: https://github.com/fazhq/faz · Python · Apache-2.0 · 2 stars

View on Hacker News