Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.
Python agentic-aiai-securityalert-triageblue-teamcybersecuritydetection-engineeringincident-responselanggraphllm-agentsmcpmitre-attackmodel-context-protocolpurple-teamsecurity-operationsself-hostedsiemsoarsocthreat-detectionthreat-intelligence
id: azure-defender
name: Microsoft Defender Connector
version: "1.0.0"
plugin_type: connector
tier: stable
description: >
Microsoft Defender (XDR / Defender for Cloud) alerts via Microsoft Graph
Security API. Pulls cross-product alerts (endpoint, identity, cloud apps,
cloud workloads) and normalizes them into AiSOC's incident schema. Requires
an Azure AD app registration with SecurityAlert.Read.All.
author: AiSOC Core Team
tags: [edr, xdr, azure, microsoft, defender, alerts]
homepage: https://github.com/beenuar/AiSOC/tree/main/services/connectors/app/connectors/azure_defender.py
license: MIT
min_aisoc_version: "4.0.0"
config_schema:
type: object
required: [tenant_id, client_id, client_secret]
properties:
tenant_id:
type: string
description: "Azure AD tenant ID (GUID)"
client_id:
type: string
description: "Application (Client) ID of the Azure AD app registration"
client_secret:
type: string
description: "Client secret for the Azure AD app registration"
secret: true