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: google-workspace
name: Google Workspace Connector
version: "1.0.0"
plugin_type: connector
tier: stable
description: >
Google Workspace audit logs (login, admin, drive, token, mobile) via the
Admin SDK Reports API. Provides identity- and SaaS-plane signal across the
Workspace surface, including suspicious-login flags and 2-step-verification
state changes. Requires a service account with domain-wide delegation and
the admin.reports.audit.readonly scope.
author: AiSOC Core Team
tags: [saas, google, workspace, gsuite, identity, audit]
homepage: https://github.com/beenuar/AiSOC/tree/main/services/connectors/app/connectors/google_workspace.py
license: MIT
min_aisoc_version: "4.0.0"
config_schema:
type: object
required: [admin_email, service_account_json]
properties:
admin_email:
type: string
description: "Super-admin email to impersonate via domain-wide delegation"
service_account_json:
type: string
description: "Service account JSON key, encrypted at rest by the credential vault"
secret: true