MCP 服务器

PentQuiver MCP Server

Enables AI assistants to search and resolve over 2,800 security commands with argument templates, allowing natural language interaction with a comprehensive command library for penetration testing.

README

PentQuiver

A blazing-fast, cross-platform command library and cheat-sheet launcher for pentesters - TUI, CLI, HTTP API and MCP server in one.

Search 2,800+ security commands, fill in the arguments, and copy or run them - from your terminal, your scripts, or your AI assistant.

PentQuiver demo

</div>

Legal notice / Aviso legal

PentQuiver is a command launcher intended solely for authorized security testing, CTF competitions and education.

You are fully responsible for how you use this tool. The author accepts no responsibility and assumes no liability for any misuse, damage, or illegal activity carried out with it. Only test systems that you own or for which you have explicit written permission.

El autor no se hace responsable del uso que se le de a esta herramienta.

This notice is also shown every time the TUI starts and must be accepted first.

Features

Fuzzy search across 2,800+ commands / 240+ tools (recon, web, Active Directory, credential access, post-exploitation, forensics and more).
Argument templates - {{arg}} and {{arg|default}} with a live preview.
Four interfaces, one core: interactive TUI, scriptable CLI, an HTTP API, and an MCP server so AI assistants can query your library.
Hexagonal architecture (ports and adapters) - clean, testable, extensible.
Cross-platform - Linux, macOS, Windows, WSL. Pure Python, no OS-specific build constraints.
Simple YAML cheat-sheets - bring your own, or use the bundled collection.

Install

pip install pentquiver              # TUI + CLI
pip install "pentquiver[api]"       # + HTTP API (FastAPI/uvicorn)
pip install "pentquiver[mcp]"       # + MCP server
pip install "pentquiver[all]"       # everything

On Linux, clipboard copy needs xclip or xsel (sudo apt install -y xclip).

Usage

pentquiver                       # launch the TUI (default)
pentquiver list nmap             # print matching commands (id + name)
pentquiver show nmap/nmap-aggressive-scan
pentquiver api --port 8000       # serve the HTTP API
pentquiver mcp                   # serve the MCP server over stdio
pentquiver --info                # project, author and support info
pentquiver --upgrade             # update to the latest release via pip
pentquiver --version

TUI keys

Key	Action
`/`	focus search, `Up`/`Down` move, `Enter` open then fill args then Copy/Run
`c`	quick-copy the raw template, `Esc` clear / back
`u`	upgrade to the latest release, `q` quit

CLI

PentQuiver CLI

HTTP API

pentquiver api            # http://127.0.0.1:8000  (interactive docs at /docs)
curl 'localhost:8000/commands?q=nmap&limit=5'
curl -X POST localhost:8000/commands/nmap/nmap-aggressive-scan/resolve \
     -H 'content-type: application/json' -d '{"values":{"target":"10.0.0.0/24"}}'

PentQuiver HTTP API

MCP (AI assistants)

Run it without installing using uv - the server is fetched and cached on first use:

{
  "mcpServers": {
    "pentquiver": {
      "command": "uvx",
      "args": ["--from", "pentquiver[mcp]", "pentquiver", "mcp"]
    }
  }
}

Or, if it is already installed (pip install "pentquiver[mcp]"):

{ "mcpServers": { "pentquiver": { "command": "pentquiver", "args": ["mcp"] } } }

Tools exposed: search_commands, list_sources, get_command, get_arguments, resolve_command.

PentQuiver MCP

Architecture

Hexagonal (ports and adapters) - the domain and use cases never depend on I/O:

pentquiver/
  domain/          entities + pure logic (Command, placeholders, fuzzy search)
  application/     ports (interfaces) + use-case service (CommandLibrary)
  adapters/
    inbound/       tui, cli, api, mcp          (driving)
    outbound/      yaml, system(clipboard/exec) (driven)
  config/          filesystem locations
  container.py     composition root (wires adapters into the service)

Swapping a data source or adding an interface means writing one adapter - the core stays untouched.

Cheat-sheet format

Drop .yml/.yaml files in your user directory:

Linux/macOS: ~/.config/pentquiver/cheatsheets/
Windows: %APPDATA%\pentquiver\cheatsheets\
or set PENTQUIVER_HOME to any directory, or pass -d PATH.

commands:
  - name: Nmap - quick TCP scan
    command: nmap -sV -sC -oA {{outfile|scan}} {{target}}
    description: Service/version detection with default scripts.
    tags: [nmap, scan, recon]

Both the native shape above and the tool/actions shape are auto-detected. The large bundled collection under pentquiver/cheatsheets/vendor/ is redistributed under the MIT license - see THIRD-PARTY-NOTICES.md.