MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Phase 1 ethical hacking reconnaissance. 14 modules, AI-validated, self-hosted, MCP-ready.
NOASSERTION -
Docker-Kali-MCPgithub.com/Foolish-admin/Docker-Kali-MCPupdated this year
AI-assisted ethical hacking framework using Kali Linux, Docker, and MCP
★ 1 -
offensive-sec-mcpgithub.com/ans-inayat/offensive-sec-mcpupdated this year
offensive security ai mcp
NOASSERTION -
blhackboxgithub.com/valITino/blhackboxupdated this year
MCP-based autonomous pentesting framework — Claude, ChatGPT, or Ollama orchestrate 70+ Kali Linux tools (nmap, sqlmap, Metasploit & more) for recon, exploitation, and post-exploitation, Wireshark packet analysis, and headless Chromium evidence capture. Fully containerized, authorization-enforced, structured pentest reports out of the box.
MIT ★ 9 -
RedVector AI - AI-powered penetration testing and cybersecurity automation framework for security researchers and ethical hackers.
NOASSERTION ★ 47 -
Empowers the AI to perform penetration testing, vulnerability assessment, reconnaissance, and security reporting — all through natural language conversation.
MIT ★ 21 -
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 finds. MCP both ways: plug in any MCP server as a tool, or drive RedAmon from Claude Code or your own agent.
MIT ★ 3,407 -
tengugithub.com/rfunix/tenguupdated this year
AI-powered penetration testing MCP server
MIT ★ 65 -
Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a proof capsule you can replay yourself.
go MIT ★ 1,829 -
bearstrike-aigithub.com/Roshu18/bearstrike-aiupdated this year
🐻 BearStrike AI: High-Signal Pentesting Console (MCP-First, Model-Agnostic). Build fast, low-noise security workflows with queue-first execution, skills-aware planning, and 150+ integrated tools.
MIT ★ 8 -
Automated-Pentest-Suitegithub.com/fdehech/Automated-Pentest-Suiteupdated this year
A dockerized Pentest-Suite capable of running AI-Powered full security checks .
★ 4 -
CLI-first, agent-native HTTP intercepting proxy & bug bounty toolkit. Headless Burp Suite alternative for AI agents (MCP), penetration testers, and ethical hackers with declarative YAML scope enforcement.
MIT ★ 2 -
kali-mcpgithub.com/Hannes221/kali-mcpupdated this year
MCP server that gives AI assistants access to a Kali Linux Docker environment for security testing
MIT ★ 5 -
AI-powered security testing for Claude Desktop. MCP server integrating 6 essential pentesting tools (nmap, nikto, sqlmap, wpscan, dirb, searchsploit) in a secure Kali Linux Docker container. Perform ethical security assessments through natural conversation.
MIT ★ 7 -
AI Pentesting Framework, Bug Bounty MCP Server, SAST/DAST Taint Engine & 12 Offensive Security Skills for Claude Code, Google Antigravity, Codex & Cursor.
MIT ★ 7 -
🛡️ Production-grade Model Context Protocol (MCP) Server for Autonomous AI Security Bug Hunting, Persistent Pentest Memory, Dynamic Checklists, Secret Redaction, and Exploit PoC Generation.
MIT ★ 1 -
RedTeam-Agentgithub.com/ktol1/RedTeam-Agentupdated this year
RedTeam-Agent: AI-Powered Autonomous Red Team Framework via Model Context Protocol. AI红队与内网渗透自动化框架,支持 gogo, fscan, httpx, nuclei, impacket, playwright 等 15+ 渗透工具,让 LLM 直接化身安全审计黑客。
★ 82 -
Open-source OSINT reconnaissance toolkit — domain intel, subdomain enum, DNS/SSL/WAF analysis, email harvest, and 16 MCP tools for Claude Desktop integration. Python 3, security-hardened.
GPL-2.0 -
Aircrack-Mcpgithub.com/R-S-Nithesh/Aircrack-Mcpupdated this year
MCP server that wraps aircrack-ng, enabling AI assistants to run and automate WiFi security assessments (scanning, handshake capture, cracking) for authorized penetration testing.
MIT ★ 1 -
Bounty OS is an evidence-driven bug bounty and security investigation platform that orchestrates reconnaissance, attack-surface discovery, vulnerability scanning, adaptive investigation, evidence collection, deterministic verification, and AI-assisted triage through a unified MCP and REST control plane.
Apache-2.0 ★ 1 -
pentest-mcp-toolkitgithub.com/KoaBrown/pentest-mcp-toolkitupdated this year
Pentest MCP Toolkit: 50 Kali Linux security tools exposed as one MCP server over Docker stdio, built to be driven 100% by AI agents (Claude Code, Codex). For authorized pentests of systems you own. You are responsible for authorization.
MIT ★ 1 -
One command installs 670+ security tools on Debian/Ubuntu/Kali, Fedora, Arch, openSUSE and Termux. Its authorization-gated MCP server runs them in a disposable Kata Containers VM sandbox for Claude Code, Codex, Gemini CLI, OpenCode and other MCP clients. 872 agent skills for CTF, pentesting, bug bounty, DFIR and red/blue teams.
oci MIT ★ 98