Empower AI agents with direct access to Defender XDR's incident management and response capabilities. Investigate, analyze, and respond to security incidents through natural language. Built for autonomous security operations.
Two specialized MCPs working together for end-to-end autonomous security operations
Query and analyze security data across Microsoft Sentinel & Defender XDR. The foundation for AI agents to understand what happened and identify threats.
Execute response actions across endpoints and identities through Microsoft Defender. Turn threat intelligence into immediate defensive action.
Every tool available to your AI agents through the Response MCP server
Stop running processes and quarantine malicious files. Requires the SHA1 hash from incident evidence.
Isolate device from network. Full isolation blocks all connections; Selective allows Outlook/Teams/Skype.
Remove device from isolation, restoring full network connectivity after threat containment.
Restrict application execution to Microsoft-signed binaries only. Blocks attacker tools from running.
Remove code execution restrictions, allowing all applications to run again after remediation.
Initiate Microsoft Defender scan. Quick scan checks common locations, Full scans entire disk.
Collect forensic package with system info, logs, memory dumps, and diagnostic data.
List recent response actions taken on machines. Filter by device, action type, or status.
Bulk isolate multiple devices in a single operation. Supports up to 100 devices at once.
Disable compromised Active Directory account via Microsoft Defender for Identity integration.
Re-enable Active Directory account after incident resolution and password reset.
Force user to change password at next logon. Critical for credential theft incidents.
Revoke all Entra ID sign-in sessions and refresh tokens. Forces re-authentication on all devices.
Mark user as compromised in Identity Protection. Sets risk level to high and triggers CA policies.
Dismiss user risk in Identity Protection. Sets risk level to none after confirming no compromise.
Mark incidents as active, resolved, or redirected with proper classification.
Assign incident to a specific analyst for investigation and remediation.
Set classification (True/False Positive) and determination for incident resolution.
Add custom tags to incidents for categorization and tracking.
Add investigation notes and comments to incident timeline for documentation.
How an AI agent handled a Mimikatz credential theft attack autonomously
Mimikatz credential theft detected with LSASS memory dump and Defender evasion attempts
The AI agent queried Sentinel to extract critical evidence and indicators:
admin@vetoniitti.com
192.168.50.40
85.76.106.83
bdc60e583c8d4ef05de010973642487bde6e1f60
040fbf1325d51358606b710bc3bd774c04bdb308
1c6913248131b5784b923eff1e76a443f738affc
fe18c58fbd0a83d67920e037d522c176704d2ca3
d1f7832035c3e8a73cc78afd28cfd7f4cece6d20
Stopped all Mimikatz processes and quarantined 4 malicious files using SHA1 hashes.
Limited execution to Microsoft-signed applications only on the SQL server.
Disabled compromised account admin@vetoniitti.com.
Executed full disk scan to detect any remaining or hidden malware.
Gathered forensic evidence including memory dumps, event logs, and system state.
Classified as True Positive - Multi-stage attack with automated response completion.
Device isolation was not performed.
A prioritized approach AI agents follow for effective incident response
When SHA1/SHA256 hashes are available in incident evidence, immediately stop processes and quarantine files. Most direct and surgical approach to neutralize active threats.
If credential theft tools detected (Mimikatz, etc.) or suspicious authentication patterns, disable affected accounts immediately to prevent lateral movement.
Limit execution to Microsoft-signed applications. Prevents attackers from running additional tools while AI agent investigates. Attacker tools are typically unsigned.
Execute full disk scan to detect dormant threats. Collect investigation package for timeline reconstruction, compliance, and post-incident analysis.
AI agents consider device isolation when:
AI agent tip: For critical servers, Selective isolation allows Outlook, Teams, and Skype while blocking other network traffic.
Response Actions
Action Execution
Integrated MCPs
Autonomous
Just describe what you want - AI agents handle the rest
// Step 1: AI agent queries Sentinel MCP "Show me high severity incidents from the past 1h" // Sentinel MCP returns incident data: Incident #171 - Mimikatz detected on vet-sql.vetoniitti.com ├── SHA1: 040fbf1325d51358606b710bc3bd774c04bdb308 (mimikatz.exe) ├── SHA1: 1c6913248131b5784b923eff1e76a443f738affc (mimilib.dll) ├── Account: admin@vetoniitti.com (COMPROMISED) ├── MITRE: T1003 (Credential Dumping), T1562 (Disable Security) └── Status: ACTIVE // Step 2: User instructs AI agent "Respond to this incident autonomously" // AI agent uses Response MCP to execute prioritized actions: ✓ StopAndQuarantine(sha1: "040fbf...", device: "vet-sql") ✓ StopAndQuarantine(sha1: "1c6913...", device: "vet-sql") ✓ StopAndQuarantine(sha1: "fe18c5...", device: "vet-sql") ✓ DisableADAccount(upn: "admin@...") ✓ RestrictCodeExecution(device: "vet-sql") ✓ RunAntivirusScan(type: "Full", device: "vet-sql") ✓ CollectInvestigationPackage(device: "vet-sql") ✓ ClassifyIncident(id: 171, class: "TruePositive") ⊘ IsolateDevice // Skipped - SQL server, business-critical // Step 3: AI agent reports back Response completed. Malware neutralized, account disabled, forensics collected. Incident #171 classified as True Positive - Multi-stage attack. Time to remediation: 47 seconds