Generally Available: Azure API Management now supports content safety controls for MCP and A2A APIs.

As organizations deploy more agentic applications and MCP-based tools, enforcing consistent safety and compliance policies across agent interactions becomes increasingly important. Many teams today rely on fragmented or custom implementations for content filtering and policy enforcement, creating operational complexity and increasing risk.

With this update, Azure API Management extends content safety capabilities to MCP tools and Agent-to-Agent (A2A) APIs, enabling centralized enforcement of safety controls across agent-based workflows.

This allows organizations to:

• Apply consistent content safety policies across models, MCP tools, and A2A agent interactions
• Reduce the risk of unsafe, harmful, or non-compliant outputs
• Centralize governance and policy enforcement for agentic systems

By bringing content safety controls into the API management layer, Azure API Management helps organizations operate AI agents and MCP ecosystems with stronger governance, compliance, and enterprise-grade safeguards.

Learn more.