Security architecture for enterprise AI agents
Bound identities, context, tools, operations, outputs, and audit evidence across the path from a user request to enterprise systems.
Read articleBack to all guidance
Guidance library
Model Context Protocol
Expose controlled resources and tools to compatible AI applications.
2 articlesGuidance library
Reviewed enterprise architecture guidance
Narrow the library by controlled topic, audience, pillar, or API product.
MCP in enterprise AI architecture
Use Model Context Protocol as a connection standard while keeping identity, authorization, business contracts, tool safety, and source operations explicit.
Read article