Microsoft Defender XDR
General

Ai Agent Real Time Protection

In brief

The documentation now lists Microsoft Foundry agents, Copilot Studio agents, and Agent 365 Tooling Servers (WorkIQ and custom MCP) as supported types. Tooling Servers cover tool invocations and responses; Foundry covers requests, responses, and tool activity, while Copilot Studio currently covers tool invocations only.

What Defender admins need to know

No administrator action is stated. Use these coverage limits when planning AI-agent protection and monitoring.

Summaries are generated from the documentation change itself.

Documentation change

The comparison below shows only the changed extract. Use the full-page view for complete context.

To detect, investigate, and hunt for AI agent threats after they occur, see Detect and investigate threats to AI agents using Microsoft Defender.

Note

Real-time protection policies currently support Microsoft Foundry agents, Microsoft Copilot Studio agents, and Agent 365 Tooling Servers (WorkIQ and Custom MCP) only. Support for additional agent types is not yet available.

Prerequisites

How real-time protection works

Real-time protection inspects AI agent activity throughout the agentic loop and blocks risky actions before they execute. Coverage depends on the agent type:

  • Agent 365 tool invocationsTooling Servers (GA): Defender integrates with Work IQ MCP to evaluate tool invocations before they run,and responses, including invocations of customer MCP tools onboarded to Agent 365. Agents that rely on unsupported tools or don't integrate with Work IQ MCP aren't covered.
  • Copilot Studio agents (Preview): Protection evaluates tool invocations, which doesn't depend on Work IQ MCP. To enable it, make sure that Copilot Studio is connected. For more information, see Enable security for AI agents using Microsoft Defender.
  • Foundry agents (Preview): Protection evaluates user requests, agent responses, tool invocations,invocations and tool responses.
  • Local AICopilot Studio agents (Preview): Covered through endpoint runtime protection in Microsoft Defender for Endpoint.Protection currently evaluates tool invocations only.

For cloud agents, thereThere are two types of real-time protection rules:

  • Default rule: Audits all agents, recording matching activity as a behavior without stopping the action. This gives you visibility before you enforce blocking.
  • Custom rules: Block matching actions before they execute and record the behavior. Create custom rules for high-confidence threats and scope them to specific agents.

When Microsoft Defender audits or blocks an action, it records the event as a behavior in the BehaviorInfo table, including what happened, why the action was considered risky, and which agent, user, and tool were involved. Security teams can query these behaviors to build custom detections, hunting queries, and downstream automation. Near-real-time detections continue to surface as alerts only in audit mode. When a blocking rule covers an agent, near-real-time alerts aren't generated for that agent.

Note