tools-mcp-bridges
Expose CLI security tools to an AI agent through MCP servers — mcp-kali-server generic terminal bridge, MetasploitMCP, pentestMCP Docker bundle, mcp-security-hub, single-tool nmap/nuclei servers. Load when setting up agent-driven tooling on Kali or wiring a new tool into MCP. Signals: mcpServers con
v2026.10.14-ee0e0c53 instalações+3 em 7 dias27 EstrelasMITsincronizado há 22 horas
Instalar
Ainda não tem a CLI da NotHoly? Instale primeiro.
$ curl -fsSL https://notholy.com/install.sh | sh$ notholy skills install noorqureshi/tools-mcp-bridgesGrava em ~/.notholy/skills depois de conferir a assinatura e o SHA-256.
AssinaturaAssinado, ed25519
Pacote4e99cddd…39996cc7
4e99cddd3639…e85e39996cc71 arquivo · 2.3 KBVarreduraBaixo1 achado
- Links para domínios externos
Fontegithub.com/NoorQureshi/security-skills/tree/main/skills/tools/tools-mcp-bridges@ee0e0c5
Este item ainda não foi escrito no seu idioma, então aparece em English.
Nesta página
When it applies
You're setting up an agent-driven workflow and need CLI tools (nmap, nuclei, sqlmap, hashcat,
gobuster, Metasploit…) callable as MCP tools instead of raw shell. This is infrastructure, not
authorization: registering a tool over MCP never widens scope — tradecraft-scope-roe and
scope.txt still gate every call. For Burp specifically, see tools-burp-suite; for attacking MCP
servers themselves, ai-mcp-security.
Why it works
MCP wraps a tool's CLI behind typed tool definitions, so the agent gets structured parameters and output instead of scraping terminal text. A generic terminal bridge (mcp-kali-server) covers everything but is unstructured; per-tool servers give safer, typed interfaces at the cost of setup.
Options (pick one per need)
| Option | Install | Tools covered | Best for |
|---|---|---|---|
| mcp-kali-server (Kali-official) | apt install mcp-kali-server |
Any terminal command (nmap, nxc, curl, gobuster…) | General-purpose; CTF/labs |
| MetasploitMCP (Kali-official) | apt install metasploitmcp |
MSF modules/payloads/sessions | MSF-heavy exploitation (tools-metasploit) |
| pentestMCP (Docker bundle) | docker run -d -p 8080:8080 ramkansal/pentestmcp |
20+: nmap, nuclei, ZAP, sqlmap, ffuf, nikto, gobuster, subfinder, httpx | One-container everything |
| mcp-security-hub (modular) | per-module pip installs | nmap, Ghidra, nuclei, sqlmap, hashcat | Enable only what you need |
| hexstrike-ai (Kali-official) | apt install hexstrike-ai |
150+ tools, multi-agent orchestration | Large-scale automation |
| Single-tool servers | npm/pip per project | one tool each (e.g. nmap-mcp-server, nuclei-mcp) | Minimal footprint |
Method
- Generic terminal bridge (start here on Kali):
bash kali-server-mcp --port 5000 # API side; runs any terminal command mcp-server --server http://localhost:5000 # MCP client-facing side - Metasploit:
metasploitmcp --transport stdio(preferred) or--transport http --port 8085. The invocation discipline intools-metasploitstill applies underneath (one-shot-x,;exit, port checks). - Docker bundle:
docker pull ramkansal/pentestmcp && docker run -d -p 8080:8080 ramkansal/pentestmcp, then register{"url": "http://localhost:8080/mcp"}in the client'smcpServers. - Register stdio servers in the client config, e.g.:
json { "mcpServers": { "kali-server": { "command": "kali-server-mcp", "args": ["--port", "5000"] }, "metasploit-mcp": { "command": "metasploitmcp", "args": ["--transport", "stdio"] } } } - Verify before relying on it: list the exposed tools and run one harmless call (e.g. a version check) against a lab target before pointing anything at a real engagement.
Gotchas
- A terminal bridge is arbitrary command execution — bind to localhost only, never expose the port on a network interface, and treat the bridge host as compromised-adjacent.
- Community MCP servers are supply chain — audit or pin versions before installing; a malicious tool server sees every command and result. Prefer Kali-official packages when they exist.
- Scope still applies — a registered scanner makes it easier to fire out-of-scope requests,
not more allowed. Keep
scope.txtloaded and check targets against it before every call. - Container bundles run as root with mounted sockets — pentestMCP's Docker has full tool capability; don't mount engagement data you can't afford to leak into it.
- Tool availability ≠ tool correctness — the server reports what its manifest claims; confirm
the underlying binary exists and is the expected version (
nmap --version, etc.).
Verify success
The MCP client lists the server's tools, a harmless invocation returns sane structured output, and every subsequent call is logged against an in-scope target in the engagement workspace.
References
Kali blog on MCP/LLM integration; Wh0am123/MCP-Kali-Server; GH05TCREW/MetasploitMCP; ramkansal/pentestMCP; FuzzingLabs/mcp-security-hub; 0x4m4/hexstrike-ai.
Portions adapted from reverse-skill by zhaoxuya520, MIT License.
Arquivos desta versão
- SKILL.md4.9 KB
Permissões
| Permissão | Declarada | Encontrada na varredura |
|---|---|---|
| Lê arquivos | Não | Não |
| Grava arquivos | Não | Não |
| Roda comandos no shell | Sim | Sim |
| Usa a rede | Sim | Sim |
| Usa conectores | Sim | Sim |
| Controla um navegador | Não | Não |
Achados da varredura
Revisado em 13 de nov. de 2026
- InfoLink · Links para domínios externos
Uma varredura limpa reduz o risco, mas não prova que o pacote é seguro. Leia o que você instala.
| Versão | Publicada em | Commit | SHA-256 | Assinatura | Mudança de permissão |
|---|---|---|---|---|---|
| v2026.10.14-ee0e0c5 | 13 de nov. de 2026 | ee0e0c5 | 4e99cddd | Assinada | – |
Mais de NoorQureshi
Tudo deste publicadorMais em IA, agentes e MCP
Ver a categoria- fal-assetsrehan-remade/fal-assets5
- ai-system-prompt-leakagenoorqureshi/ai-system-prompt-leakage4
- ai-prompt-injectionnoorqureshi/ai-prompt-injection4
- testing-prompt-injection-in-rag-pipelinesmukul975/testing-prompt-injection-in-rag-pipelines4
- implementing-llm-guardrails-for-securitymukul975/implementing-llm-guardrails-for-security4
- defending-llms-with-guardrailsmukul975/defending-llms-with-guardrails4
Pergunte tudo o que o seu escopo permite.
Crie a conta, adicione créditos e faça a primeira pergunta no chat ou no terminal.
- 1/3
Crie a conta
Individual ou empresa. Dá para virar empresa depois sem perder saldo nem chaves.
Pessoa físicaEmpresa - 2/3
Adicione créditos
No cartão. Você paga por token, sem assinatura.
$5.00recarga mínima - 3/3
Pergunte
No chat, ou instale o CLI e rode notholy login no terminal.
$ notholy login