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: abnormal_security
name: Abnormal Security Connector
version: "1.0.0"
plugin_type: connector
tier: stable
description: >
Abnormal Security behavioural-AI email threat events. Polls /v1/threats
and /v1/cases for BEC, credential phishing, account takeover, and
invoice-fraud detections, then normalises them to the AiSOC alert shape
with a high/medium/low severity ladder.
author: AiSOC Core Team
tags: [email-security, saas, bec, phishing, abnormal]
homepage: https://github.com/beenuar/AiSOC/tree/main/services/connectors/app/connectors/abnormal_security.py
license: MIT
min_aisoc_version: "4.0.0"
config_schema:
type: object
required: [api_token]
properties:
base_url:
type: string
description: API base URL. Defaults to https://api.abnormalplatform.com.
api_token:
type: string
description: Bearer token issued from Abnormal Console → Settings → Integrations → API.
secret: true