0xSteph/pentest-ai — Offensive-security MCP server with 197 wrapped tools, 17 specialist agents, and 14 SPA-aware probes…

Description and use

The 0xSteph/pentest‑ai project provides a modular offensive‑security command‑and‑control (MCP) server that bundles 197 pre‑wrapped penetration‑testing tools, 17 specialized agents, and 14 SPA‑aware probes designed to discover vulnerabilities that automated scanners often overlook. It offers both a powerful CLI and an extensible MCP framework, allowing users to plug in their own large language models (BYO LLM) for custom analysis and automation. The open‑source stack targets AI/ML‑enhanced backend and dev‑tool workflows for advanced red‑team operations.

Problem

0xSteph/pentest-ai helps connect AI assistants to real tools and data through a standard protocol.

Outcome

Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.

Workflow

• connect AI agents to tools
• ship Model Context Protocol servers
• standardize integrations

Evidence

Offensive-security MCP server with 197 wrapped tools, 17 specialist agents, and 14 SPA-aware probes that catch bugs scanners miss. CLI + MCP, BYO LLM.

Source