Defend-AI-Tech-Inc/agent-discover-scanner
Multi-layer AI agent detection: Static code analysis, network monitoring, and Kubernetes runtime visibility with eBPF.
Detects unaccounted-for AI systems by correlating static code analysis, live network traffic, and Kubernetes eBPF runtime data—identifying "GHOST agents" making real API calls with no source code or owner record. Includes SaaS blast-radius mapping (which external services each agent actively connects to), high-risk autonomous platform detection (OpenClaw, etc.), and Model Context Protocol (MCP) server verification across all AI clients. Works across developer machines, CI/CD pipelines, and clusters via osquery, Tetragon, and passive network observation.
Available on PyPI.
Stars
8
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Dependencies
9
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Defend-AI-Tech-Inc/agent-discover-scanner"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AgentSeal/agentseal
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor...
Nebulock-Inc/agentic-threat-hunting-framework
ATHF is a framework for agentic threat hunting - building systems that can remember, learn, and...
cosai-oasis/secure-ai-tooling
The CoSAI Risk Map is a framework for identifying, analyzing, and mitigating security risks in...
HeadyZhang/agent-audit
Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis....
oasm-platform/open-asm
Open-source platform for cybersecurity Attack Surface Management (OASM).