agentic_security
★ 2.0k
vs
jadx-ai-mcp
★ 2.9k
agentic_security vs jadx-ai-mcp
agentic_security: Agentic Security is an open-source vulnerability scanner designed to protect AI systems and LLM agent workflows. It detects and mitigates threats like jailbreaks, fuzzing, and multimodal attacks.; jadx-ai-mcp: JADX-AI-MCP is a plugin for the JADX decompiler that integrates with Model Context Protocol (MCP) to provide live reverse engineering support using LLMs like Claude. It offers a real-time workflow for Android APK analysis, encompassing decompilation, context-aware code review, and AI-driven recommendations.
01
TL;DR
agentic_securitySecurity & Safety · ★ 2.0k
When to choose:
- You want to red-team your own LLM or agent endpoint with multimodal attacks, multi-step jailbreaks, fuzzing and RL-based probes.
- Your target is any HTTP API: you describe it with a plain-text request spec.
- You want a CI check with a budget and a failure threshold, and your own CSV prompt datasets.
When to skip:
- You are not authorised to test the target: only scan systems you own or may test.
- You need to vet MCP servers before installing them: it tests model endpoints, not MCP server code.
- API cost is a problem: scans send many attack prompts.
jadx-ai-mcpSecurity & Safety · ★ 2.9k
Basic Code Understanding (e.g., explaining class functionality, summarizing method responsibilities).
02
Side-by-Side Comparison
Field
agentic_securityjadx-ai-mcpCategory
Security & Safety
Security & Safety
Stars
★ 2.0k
★ 2.9k
License
Apache-2.0
Apache-2.0
Install Command
pip install agentic_security
jadx plugins --install "github:zinja-coder:jadx-ai-mcp"
Updated
1w ago
1w ago
Open Source
Yes
Yes
Tags
AI Security, LLM, Vulnerability Scanner
JADX, Android, Reverse Engineering
03
Features
agentic_security01Multimodal Attacks
02Multi-Step Jailbreaks
03Comprehensive Fuzzing
04API Integration & Stress Testing
05RL-Based Attacks
jadx-ai-mcp01Automated LLM communication for Android APK analysis.
02Real-time vulnerability detection and reverse engineering assistance.
03Integration with JADX decompiler via Model Context Protocol (MCP).
04Support for various LLM clients like Claude, LM Studio, and Cherry Studio.
05Extensive set of MCP tools to interact with decompiled code, resources, and debugger.
04
Use Cases
agentic_security↳AI system vulnerability testing
↳LLM security research
↳DevSecOps for AI
jadx-ai-mcp↳Basic Code Understanding (e.g., explaining class functionality, summarizing method responsibilities).
↳Vulnerability Detection (e.g., checking for hardcoded secrets, insecure API usages).
↳Reverse Engineering Helpers (e.g., code deobfuscation and renaming, inferring original purpose of smali methods).
05
Best For
agentic_securityTrending
jadx-ai-mcpTrending
FAQ
FAQ
What is the difference between agentic_security and jadx-ai-mcp?
Both agentic_security and jadx-ai-mcp are in the Security & Safety category. agentic_security has 2.0k stars, while jadx-ai-mcp has 2.9k stars.
Which is better, agentic_security or jadx-ai-mcp?
The best choice depends on your use case. Choose agentic_security if AI system vulnerability testing, and jadx-ai-mcp if Basic Code Understanding (e.g., explaining class functionality, summarizing method responsibilities)..
Is agentic_security free or open source?
Yes, agentic_security is open source on GitHub (Apache-2.0).
Is jadx-ai-mcp free or open source?
Yes, jadx-ai-mcp is open source on GitHub (Apache-2.0).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→