Skip to content
Agent

Appendix F-1.1 — AI Agents

by Elie-Saliba

AI Summary

A modular framework for building security-focused AI agents (Detection, Advisor, Quality) that integrate with MCP servers and multiple LLM providers. Developers building security automation tools and threat analysis pipelines benefit from its extensible architecture and shared tooling.

Install

Copy this and paste it into Claude Code, Cursor, or any AI assistant:

I want to set up the "Appendix F-1.1 — AI Agents" agent in my project.

Please run this command in my terminal:
# Add AGENTS.md to your project root
curl --retry 3 --retry-delay 2 --retry-all-errors -o AGENTS.md "https://raw.githubusercontent.com/Elie-Saliba/security-projects-meta/master/Appendices/ai-security/as-ai-agents.md"

Then explain what the agent does and how to invoke it.

Description

Meta repository for security projects with submodules and shared documentation

Overview

All AI agents extend BaseAgent and use the Codex SDK for LLM interactions with Model Context Protocol (MCP) tool support. The system is provider-agnostic and scalable, any LLM provider can be used by swapping the Codex instance in BaseAgent with a compatible API client. `mermaid graph TD BaseAgent[BaseAgent] --> DA[DetectionAgent] BaseAgent --> AA[AdvisorAgent] BaseAgent --> QA[QualityAgent] DA -.uses.-> MCP1[Detection MCP Server<br/>Port 3100] AA -.uses.-> MCP2[Advisor MCP Server<br/>Port 3101] QA -.uses.-> MCP3[Quality MCP Server<br/>Port 3102] MCP1 --> Tools1[Tools:<br/>- get-Logs<br/>- search-logs<br/>- get-related-logs<br/>- get-mitre-tactics<br/>- get-mitre-techniques<br/>- get-owasp-info] MCP2 --> Tools2[Tools:<br/>- get-Logs<br/>- get-mitre-tactics<br/>- get-mitre-techniques<br/>- get-owasp-info<br/>- search-remediation-examples] MCP3 --> Tools3[Tools:<br/>- get-Logs<br/>- get-feedback-patterns<br/>- search feedback-patterns] `

MCP Tools Available

• getLogs: Fetch additional logs for context • getMitreTactic: Get MITRE ATT&CK tactic details • getMitreTechnique: Get MITRE ATT&CK technique details • getOwaspInfo: Get OWASP category information

MCP Tools Available

• getLogs: Fetch additional context • getMitreTactics: List all MITRE tactics • getMitreTactic: Get specific tactic details • getMitreTechniques: Search techniques • getMitreTechnique: Get specific technique details • getOwaspCategories: List OWASP categories • getOwaspInfo: Get category details • searchRemediationExamples: Find similar past detections

Appendix F-1.1 — AI Agents

Comprehensive documentation for AI agents powered by Codex SDK and MCP.

Discussion

0/2000
Loading comments...

Health Signals

MaintenanceCommitted 3mo ago
Stale
AdoptionUnder 100 stars
0 ★ · Niche
DocsMissing or thin
Undocumented

GitHub Signals

Issues0
Updated3mo ago
View on GitHub
No License

My Fox Den

Community Rating

Sign in to rate this booster

Works With

Claude Code
Claude.ai