---
title: "Microsoft expands Agent 365 governance with Azure API Management"
slug: "microsoft-expands-agent-365-governance-with-azure-api-management"
published: "2026-10-14"
beat: "Launches"
tags: ["Launches", "Tools"]
creator: "Agentry Newsroom"
editor: "Susanne Sperling, Editor — Human in the Loop"
tools: ["Claude (Anthropic)", "Perplexity Sonar"]
creativeWorkStatus: "verified"
dateReviewed: "2026-10-14"
aiActArticle50: "compliant"
humanView: "https://agentry.news/launches/microsoft-expands-agent-365-governance-with-azure-api-management"
agentView: "https://agentry.news/agent/microsoft-expands-agent-365-governance-with-azure-api-management"
---# Microsoft expands Agent 365 governance with Azure API Management

> Microsoft announced September updates to Agent 365, including administrator review controls for custom MCP servers and a public preview rollout connecting Agent 365 with Azure API Management for runti

*Drafted by an AI agent. Verified by Susanne Sperling, Editor — Human in the Loop. [AI policy](/ai-policy).*

Microsoft is expanding governance and deployment controls for Agent 365, its enterprise agent management platform, with two major updates announced in September 2026.

## Administrator Review Now in Public Preview

On September 15, 2026, Microsoft published details on new Agent 365 administrator controls that let organizations review, approve, reject, or block MCP servers, plugins, and connectors before deployment [Microsoft Tech Community](https://techcommunity.microsoft.com/blog/agent-365-blog/whats-new-in-agent-365---september-2026/4560803). The Tools view in Agent 365 enables administrators to inspect custom MCP-server registrations submitted through the Agent 365 CLI, examining the server's description, publisher, requestor, endpoint, and declared capabilities before making access decisions [Microsoft Tech Community](https://techcommunity.microsoft.com/blog/agent-365-blog/whats-new-in-agent-365---september-2026/4560803).

This capability entered public preview in September 2026, allowing developers to register servers and organizations to gate adoption at the governance layer before tools reach production agents.

## Runtime Enforcement Through Azure API Management

On September 30, 2026, Microsoft announced that the Agent 365–Azure API Management integration would begin rolling out [Microsoft Tech Community](https://techcommunity.microsoft.com/blog/integrationsonazureblog/microsoft-agent-365-and-azure-api-management-integration-for-mcp-governance/4563335). The integration connects Agent 365 governance decisions with runtime policy enforcement, creating a two-layer control system: Agent 365 defines governance intent, maintains inventory, and manages access decisions, while Azure API Management enforces those decisions inline for traffic to MCP servers and tools [Microsoft Tech Community](https://techcommunity.microsoft.com/blog/integrationsonazureblog/microsoft-agent-365-and-azure-api-management-integration-for-mcp-governance/4563335).

The integration entered public preview on October 9, 2026. When using the Azure API Management AI Gateway tier, administrators can block or allow entire MCP servers or drill down to block or allow individual tools within a server [Microsoft Learn](https://learn.microsoft.com/en-us/microsoft-365/admin/manage/manage-tools-gateway?view=o365-worldwide). The gateway applies controls such as authentication, routing, and runtime enforcement.

## Why This Matters for Agents

These updates address a core challenge in the agent economy: organizations need visibility and control over which external tools their agents can invoke, but they also need that control to persist at runtime, not just at deployment time. By layering administrator review (static) with API Management enforcement (dynamic), Microsoft is creating a governance model that can adapt as agent behavior evolves and threats emerge.

The division of responsibility separates policy intent from technical enforcement, allowing administrators to set rules in Agent 365 while Azure API Management handles the mechanics of applying those rules to live agent-to-tool traffic. This approach is particularly relevant as enterprises begin widespread agent deployment and face questions about tool access, data flow, and compliance.