<div align="center">

🐉 kali-mcp

Your AI, holding a full Kali Linux toolkit.

kali-mcp turns any MCP-compatible AI assistant into a hands-on penetration testing partner — it drives 20+ real Kali security tools through 101 AI-callable actions, and hands the AI clean, verified, structured findings instead of raw terminal noise.

101 MCP tools · 20+ Kali binaries · 21 finding extractors · 7 attack-chain templates · 25 CVE remediations · ~315 tests

Quick Start · Documentation · Tool Reference

</div>

---

You:  "Scan 10.10.10.5 and tell me what's worth attacking."

AI:   → scan_host("10.10.10.5")
      → open ports 22, 80, 445 — fans out nikto + gobuster + nuclei + enum4linux in parallel
      → 14 findings extracted, verified, and deduplicated
      → attack chain found:  Exposed .git  →  leaked creds  →  Admin Panel
      → next moves suggested:  hydra on SSH, sqlmap on the login form

You describe intent. The AI drives the tools. kali-mcp makes the results trustworthy.

✨ Why kali-mcp

• 🧠 Structured, not raw. Every scan result becomes a clean finding (host, severity, confidence, evidence) — never a wall of terminal text. → The Finding Pipeline
• 🎯 Low false positives. Findings are actively re-verified (soft-404 baselines, catch-all clustering, .git/.env content proof), evidence-anchored, and cross-tool corroborated. The AI can't inflate what the tools didn't prove. → False-Positive Reduction
• 🔗 Impact, not just bugs. Individual findings are correlated into named attack chains with ready-to-paste narratives. → Attack Chains
• 🛰️ Change detection. Passive recon sweeps diff against previous runs and surface newly exposed assets — where the bounties are. → Continuous Recon
• 🗂️ Memory. A persistent asset inventory and full engagement lifecycle, from scope to client-ready report. → Engagements
• 🔒 Safety-first. stdio-only (no exposed network), scope allow/deny enforcement, argument-injection guards, an encrypted credential vault, and a full audit log. → Security Model

🚀 Quick Start

# 1. Clone & install
git clone https://github.com/Neeraj829784/kali-mcp.git
cd kali-mcp
python3 -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"

# 2. Verify
python3 -c "from server import mcp; print('Ready')"

Then point your AI client at it:

{
  "mcpServers": {
    "kali-mcp": {
      "command": "/path/to/kali-mcp/.venv/bin/python",
      "args": ["/path/to/kali-mcp/server.py"]
    }
  }
}

Ask it to run server_health() to confirm the tools are installed, then scan_host("<your-authorized-target>").

Full setup — including the security tools kali-mcp drives — is in the Installation guide.

📚 Documentation

Everything lives in docs/:

Start here	Concepts	Scope & assets	Reference
Installation	Finding Pipeline	Program Scope	Tool Reference
Configuration	False-Positive Reduction	Asset Inventory	Security Model
Workflows	Attack Chains	Continuous Recon	Deployment
Engagements			Testing

⚖️ Responsible use

kali-mcp runs real offensive tooling. Only test systems you own or are explicitly authorized to test. Use programs to encode your authorization boundary and stay inside it. You are responsible for how you use this tool.

📄 License

MIT — see LICENSE.