MCP servers and skills: search, filter by where they run, and compare.
1–24 of 253 tools for “ai-pentesting”
Clear allAI-Pentesting-Tool is an educational workflow for using an AI agent with Kali tooling through MCP (Model Context Protocol) in VS Code insiders for white-box and black-box pentesting..
MCPLink only★ 7
A comprehensive AI-powered penetration testing system using the Model Context Protocol (MCP), Docker, and Kali Linux tools.
MCPLink onlyFew stars
A practical, community-driven checklist for pentesting MCP servers. Covers traffic analysis, tool-call behavior, namespace abuse, auth flows, and remote server risks. Maintained by Appsecco and licens
SkillCC-BY-4.0★ 42No key
🔐 50+ MCP Security Servers for AI-Powered Pentesting | Integrate Nmap, Burp Suite, Nuclei, Shodan, BloodHound, Semgrep, Trivy | Model Context Protocol for Cybersecurity
SkillMIT★ 34No key
Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a proof capsule you can replay yourself.
PythonMIT★ 1.8kNo key
Open-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens PRs that fix what it
SkillMIT★ 3.2kNo key
Open-source AI penetration testing tool to find and fix app vulnerabilities (mirror of usestrix/strix, Apache-2.0)
SkillApache-2.0★ 1Few starsNo key
AI-powered security agent that scans codebases and pull requests for vulnerabilities in CI/CD pipelines.
SkillApache-2.0★ 4Few starsNo key
🛡 The reference playbook for pentesting AI chatbots & LLM-powered apps in one place. Ready-to-use payloads covering the full OWASP LLM Top 10 plus frontier vectors (MCP · RAG · A2A · computer-use · v
MCPLink only★ 39
Run autonomous AI pentesting agents to find and fix security gaps before attackers do
MCPLink only★ 2Few stars
Claude Code skill for autonomous AI pentesting with Keygraph Shannon
SkillLink only★ 2Few stars
Open-source AI cybersecurity agent/harness
SkillApache-2.0★ 4Few starsNo key
This project contains necessary guides to get a mcp centric pentesting setup up.
SkillCC0-1.0★ 1Few starsNo key
BugWolf — all-round bug bounty hunting skill for Claude Code: parallelized agents for smart contract audits (EVM, Move, Solana, TRON), web/API security, CI/CD attacks, LLM/agentic AI security, and sub
SkillApache-2.0★ 1Few starsNo key
Autonomous AI penetration testing agent. Plans attack path, executes multi-phase pentest (recon→scan→exploit→report), scores with CVSS 3.1. Pure Python stdlib. Zero extra dependencies.
SkillMIT★ 3Few starsNo key
AI pentesting: run scans, triage vulnerabilities, review PRs, manage schedules and assets.
Hosted by authorNo licenseFew starsNo key
Universal AI pentesting skill extracted from usestrix/strix — portable .agents/ knowledge module
SkillLink only★ 7
CARMA is the production server that makes JSON-AM usable. It resolves memory://, context://, trace:// URIs over HTTP, verifies JWT capability tokens, signs envelopes with JWS Ed25519, and exposes memo
SkillApache-2.0★ 1Few starsNo key
Stdlib-only Python MCP server with three security tools: CVE lookup via OSV.dev, host exposure via Shodan InternetDB, and orchestration of a locally installed Nuclei scanner. No exploit code bundled;
PythonMITFew starsNo key
Web Application Pentest for Hunting some bugs in web application
SkillMIT★ 8No key
Multi-agent, model-agnostic AI pentesting harness: recon -> exploit -> verify pipeline with a Kali attack box, scoped tool access, HITL approval gates, and full audit trails per agent.
MCPLink only★ 3Few stars
An 8 - node physical and virtual enterprise homelab for AI Pentesting, Model Context Protocol (MCP) security, and LLM adversarial engineering.
MCPLink only★ 2Few stars
SkillMIT★ 4Few starsNo key
Who stands behind it
