Straza™ blog: runtime AI agent governance https://straza.ai/blog/ Engineering notes from building Straza™ and the identity-governance side of AI agents: MCP servers, IGA connectors, approval flows. en Thu, 17 Sep 2026 17:43:02 +0000 Role-based access control for AI agents https://straza.ai/blog/straza-role-model/ https://straza.ai/blog/straza-role-model/ Wed, 09 Sep 2026 09:00:00 +0000 An MCP server is a target system and its tools are entitlements. From there the role model falls out: four kinds of role, and your IGA sees each of them as a role it already knows how to certify. Your IGA can already govern AI agents https://straza.ai/blog/iga-already-governs-agents/ https://straza.ai/blog/iga-already-governs-agents/ Mon, 24 Aug 2026 09:00:00 +0000 Give each agent an identity, a sponsor, and roles your IGA can assign and review. Straza enforces that access when the agent calls a tool.