---
title: "PentestMCP: A Toolkit for Agentic Penetration Testing (arXiv:2510.03610) | Papers With Code Cyber"
description: "Agentic AI is transforming security by automating many tasks being performed manually. While initial agentic approaches employed a monolithic architecture, the…"
canonical: "https://paperswithcode-cyber.com/paper/2510.03610"
type: "paper"
---

# PentestMCP: A Toolkit for Agentic Penetration Testing

arXiv:2510\.03610 · 2025-10-04

Authors: Zachary Ezetta, Wu\-chang Feng

## Abstract

Agentic AI is transforming security by automating many tasks being performed manually\. While initial agentic approaches employed a monolithic architecture, the Model\-Context\-Protocol has now enabled a remote\-procedure call \(RPC\) paradigm to agentic applications, allowing for the flexible construction and composition of multi\-function agents\. This paper describes PentestMCP, a library of MCP server implementations that support agentic penetration testing\. By supporting common penetration testing tasks such as network scanning, resource enumeration, service fingerprinting, vulnerability scanning, exploitation, and post\-exploitation, PentestMCP allows a developer to customize multi\-agent workflows for performing penetration tests\.

## Tasks

- [Penetration testing](https://paperswithcode-cyber.com/tasks/cyberintel-penetration-testing)

## Code repositories

- [Craftzman7/pentest\-mcp](https://github.com/Craftzman7/pentest-mcp)

## Paper resources

- [Abstract page](https://arxiv.org/abs/2510.03610v1)
- [PDF](https://arxiv.org/pdf/2510.03610v1.pdf)