by morluto · MCP Server · ★ 398
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Reverse engineer anything with agents, from app behavior down to native binaries.
| Stars | 398 |
| Forks | 31 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 52.0310638192928/100 |
| Open Issues | 41 |
| Last Updated | 2026-09-08 |
| Created | 2026-04-14 |
| Platforms | cli, mcp, node |
| Est. Tokens | ~13k |
Looking for a rea alternative? If you're comparing rea with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against grou
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 comman
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code ·
The control plane for AI coding agents.
Open-source AI reverse-engineering agent platform and MCP server for Ghidra, Frida, x64dbg and Rizin — automat
Automate Ghidra reverse engineering from the command line — headless analysis, decompilation, and structured J
Explore other popular mcp server tools:
rea is Reverse engineer anything with agents, from app behavior down to native binaries.. It is categorized as a MCP Server with 398 GitHub stars.
rea is primarily written in TypeScript. It covers topics such as agent-skills, ai-agent-tools, ai-agents.
You can find installation instructions and usage details in the rea GitHub repository at github.com/morluto/rea. The project has 398 stars and 31 forks, indicating an active community.
rea is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to rea on Agent Skills Hub include reverify, roam-code, memtrace-public. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: