{"slug":"fpytloun/intaris","name":"Intaris","description":"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.","category":"other","tags":[],"official":false,"stars":14,"transport":"http","install":[{"cmd":"uvx intaris","imports":[]}],"tools":[{"name":"intaris","description":"Guardrails service for AI agents that evaluates every tool call for safety and alignment before allowing execution. Works with MCP-compatible clients."}],"env_vars":["LLM_API_KEY","INTARIS_URL"],"auth_type":"none","github":"https://github.com/fpytloun/intaris","homepage":"","server_url":"","status":"active","source":"mcpservers.org","updated_at":"Thu May 28"}