Microsoft Expands AI Agent Governance with MCP Firewall

Microsoft has expanded its governance framework for AI agents with the introduction of the MCP Firewall. This new component is part of the Global Secure Access suite and provides centralized visibility and runtime protection for Model Context Protocol (MCP) traffic.

The firewall acts as a policy boundary between an AI agent and its broader ecosystem of tools and servers, enforcing Zero Trust policies on specific methods and resources an agent attempts to access. This development arrives as the fourth layer in an emerging governance stack, joining existing solutions like Okta Agent SSO, IBM AgentOps, and Broadcom AgentMinder.

The MCP Firewall is currently in Public Preview and provides a necessary mechanism to bring order to the chaotic growth of agentic tool usage. It controls which specific tools, prompt templates, or protocol versions an agent is permitted to use, addressing the 'what' of the interaction.