Mergen is an MCP server that gives your AI a real red team brain. It doesn't just run tools, it picks the right ones, chains them together, and actually makes sense of the output. Built by pentesters, for pentesters who are tired of babysitting scripts.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"mergen-ai": {
"args": [
"/path/to/mergen_mcp.py",
"--server",
"http://KALI_IP:8000"
],
"command": "python3",
"timeout": 300,
"disabled": false,
"description": "Mergen (BETA) — AI-Powered Red Team MCP Server"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
AI-native MCP server that gives Claude, Cursor, Antigravity and any MCP-compatible agent full penetration testing capabilities — autonomous planning, adaptive execution, and professional reporting across 44+ security tools.
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in security
An evil MCP server used for redteam testing
Proof primitive for AI agents on MultiversX. Anchor file hashes on-chain as verifiable proofs.
AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
Security-first platform for AI agents. 38 specialized agents, 15 AI-powered extensions, zero-knowledge multi-agent orchestration. SENTINEL WAF, Ed25519 auth, 2.6M grounding facts.
MCP Security Weekly
Get CVE alerts and security updates for Mergen Mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
AI-native MCP server that gives Claude, Cursor, Antigravity and any MCP-compatible agent full penetration testing capabilities — autonomous planning, adaptive execution, and professional reporting across 44+ security tools.
Architecture • Installation • AI Agent Setup • MCP Commands • Tool Arsenal • API Reference • Troubleshooting
Mergen BETA features a multi-layer architecture combining a FastAPI backend, an adaptive AI attack engine, and a plugin system with automatic discovery.
graph TD
A[AI Agent - Claude / Cursor / GPT] -->|MCP Protocol - stdio or SSE| B[mergen_mcp.py - MCP Proxy]
B -->|HTTP REST| C[server.py - FastAPI Core]
C --> D[AI Attack Engine]
C --> E[Process Manager]
C --> F[Memory Engine]
D --> G[TargetProfiler]
D --> H[KillChainBuilder - 41 chains]
D --> I[AdaptiveExecutionEngine]
F --> J[Operation History]
F --> K[Learning Database]
F --> L[Recon Cache - TTL]
C --> M[Plugin Manager - 44 tools]
M --> N[Recon Plugins]
M --> O[Web Security Plugins]
M --> P[Exploit Plugins]
M --> Q[Binary Analysis Plugins]
C --> R[Correlation Engine]
C --> S[Defense Detector]
C --> T[Playbook Selector]
C --> U[Dashboard - WebSocket]
C --> V[SQLite - sessions.db]
style A fill:#4a0000,color:#fff
style B fill:#6a0000,color:#fff
style C fill:#8b0000,color:#fff
style D fill:#333,color:#fff
style M fill:#333,color:#fff
TargetProfiler classifies the target (IP, domain, URL, CIDR) and identifies the technology stack.KillChainBuilder selects from 41 predefined attack chains based on target type and operator mode.AdaptiveExecutionEngine runs tools in sequence, updating the plan dynamically as results arrive.| Requirement | Version |
|---|---|
| Operating System | Kali Linux (recommended), Debian/Ubuntu |
| Python | 3.10+ |
| Disk Space | ~2 GB with all tools installed |
| RAM | 2 GB minimum, 4 GB recommended |
git clone https://github.com/g4sk0/mergen-mcp.git
cd mergen-mcp
sudo bash install.sh
install.sh handles everything automatically:
requirements.txtaptmergen command on system PATHsystemd service for persistent operationgit clone https://github.com/g4sk0/mergen-mcp.git
cd mergen-mcp
python3 -m venv venv
sour
... [View full README on GitHub](https://github.com/g4sk0/mergen-mcp#readme)