Secure AI, end to end.
with Microsoft technologies
Practical scenarios, capability mappings, and guidance to secure AI end to end across your estate — from identity and data to infrastructure and agents.
One connected knowledge graph
Every page here is a node in one connected graph. Start from a challenge you face, a product you already own, or a control you need — and follow the links to everything related.
Latest updates
See all updates →- Block Unsanctioned AI Destinations Blocks access to unsanctioned AI apps at the network layer — enforcing org-wide blocking through Defender for Cloud Apps and applying user and group-level restrictions through Entra Internet Access.
- MCP Firewall (Preview) Allows or blocks remote MCP servers and individual tools, resources, or prompt templates in user-scoped traffic, including traffic from agents on managed devices; currently in preview. Requires the Global Secure Access client and TLS inspection, and inspects streamable HTTP and Server-Sent Events traffic only, excluding local MCP servers and stdio transport.
- An introduction to agent identities Understand what an agent identity represents, how Microsoft platforms create it, and when the Agent 365 SDK is needed. Learn the basic decisions about access and accountability before deploying an agent.