Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
vet-mcp checks open source packages—like those suggested by AI coding tools—for vulnerabilities and malicious code. It supports npm and PyPI, and runs locally via Docker or as a standalone binary for fast, automated vetting.
JADX-AI-MCP is a plugin and MCP Server for the JADX decompiler that integrates directly with Model Context Protocol (MCP) to provide live reverse engineering support with LLMs like Claude.
Quality signal
52/100 (Fair)
59/100 (Good)
Install path
Remote · high
npx · low
Engagement
3 0 0 1,096
3 0 0 2,616
Tools
Real-time malicious package detection via SafeDep CloudVulnerability analysis based on dependency usage evidencePolicy-as-code enforcement with CEL expressionsSupports npm, PyPI, Maven, Go, Ruby, Rust, PHP ecosystemsScans container images and SBOMsOutputs actionable reports in multiple formats
MCP server integrated into JADX-GUI for live AI interactionAccess to full source, methods, fields, and smali via MCP toolsBuilt-in Claude Desktop integration for contextual code queriesSupports real-time AI-driven code review and recommendationsLocal loopback MCP client interoperability