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: aws-guardduty
name: AWS GuardDuty Connector
version: "1.0.0"
plugin_type: connector
tier: stable
description: >
AWS GuardDuty threat detection. Pulls findings directly from the native
GuardDuty API (not Security Hub) for richer per-finding context including
network connection action, runtime details, EKS audit shape, and S3 access
patterns. One connector per region.
author: AiSOC Core Team
tags: [cloud, aws, guardduty, threat-detection, native]
homepage: https://github.com/beenuar/AiSOC/tree/main/services/connectors/app/connectors/aws_guardduty.py
license: MIT
min_aisoc_version: "7.1.0"
config_schema:
type: object
required: [region]
properties:
region:
type: string
description: AWS region the GuardDuty detector lives in.
default: "us-east-1"
access_key:
type: string
description: >
IAM access key ID. Leave blank to use the runtime IAM role /
instance profile, which is the recommended production posture.
secret_key:
type: string
description: >
IAM secret access key. Required only when supplying a static
access key above.
secret: true