Intaris

httpnone★ 14other

Guardrails service for AI agents. Default-deny tool call evaluation with LLM safety analysis, priority-ordered decision matrix, and human-in-the-loop escalations. Session recording, behavioral analysis, MCP proxy, secret redaction, and real-time audit.

github ↗

Install

How to run this server

[ { "cmd": "uvx intaris", "imports": [] } ]

server path: intaris

Tools

What this server exposes

intaris

Guardrails service for AI agents that evaluates every tool call for safety and alignment before allowing execution. Works with MCP-compatible clients.

Configuration

Environment & auth

authnone

envLLM_API_KEY

envINTARIS_URL

Resources

githubhttps://github.com/fpytloun/intaris ↗