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.
-
ai-pentest-suitegithub.com/CatNotBat/ai-pentest-suiteupdated this year
Autonomous IoT/firmware pentest agent — Claude Code in Kali with MCP servers for nmap, john, UART, searchsploit, CVE lookup
MIT -
A comprehensive AI-powered penetration testing system using the Model Context Protocol (MCP), Docker, and Kali Linux tools.
-
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 -
基于 LLM Agent + MCP 的自动化安全侦察框架:自然语言驱动 nmap / subfinder / httpx,完成子域枚举 → Web 探测 → 端口扫描 → 中文报告闭环(仅限已授权场景,只做侦察不做利用)
Apache-2.0 -
nobody-pentest-mcpgithub.com/nobody0x/nobody-pentest-mcpupdated this year
MCP server for Nobody AI Pentest Engine v2 — real tool execution (nmap, httpx, CVE APIs) via Claude Code
pypi MIT -
Pentest with any AI agent — one MCP server & CLI orchestrating Semgrep, Trivy, SQLMap and Nuclei, with a human-only authorization scope enforced in code.
npm MIT -
Automated-Pentest-Suitegithub.com/fdehech/Automated-Pentest-Suiteupdated this year
A dockerized Pentest-Suite capable of running AI-Powered full security checks .
★ 4 -
mcp-pentestgithub.com/allsmog/mcp-pentestupdated this year
MCP server for authorized pentest workflows: Nmap/Gobuster orchestration, context aggregation, AI-assisted triage, and reporting.
MIT ★ 24 -
Authorization-gated penetration testing MCP server for AI agents - 80 tools (recon, vuln scanning, web app, exploit, CTF, reporting) with engagement-file scope enforcement. pipx install pentester-mcp
pypi MIT ★ 2 -
pentester-mcpgithub.com/halilkirazkaya/pentester-mcpupdated this year
Elevate your AI assistants (like Claude & Cursor) into autonomous cybersecurity experts. Pentester-MCP integrates 200+ pentesting tools via the Model Context Protocol (MCP) using a secure Docker sandbox.
MIT ★ 61 -
Offensive-security tools, skills, and MCP servers for local AI agents — privacy-first, small-model-driven. Authorized pentest/red-team companion: 6 MCP servers (27 tools), all irreversible classes human-gated.
Apache-2.0 -
AI-orchestrated, Kali-native pentesting lab: an MCP tool-server with scope/VPN/rate/audit enforced in code, independent finding verification, MITRE ATT&CK + OWASP mapping, a reusable findings library, retest tracking, WireGuard OPSEC, LUKS encryption, and automated PDF reports.
MIT ★ 19 -
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 -
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 -
KhaosMCP is a local-first, agent-operated pentest platform using AI via MCP. It connects the external operator to the complete assessment cycle: scoping, supervised execution, integrations, evidence gathering, review of findings, and reporting.
★ 5 -
Android Pentest AI Assistant (APAIA) is an MCP server for Claude AI that was specifically created for Android pentesting/bug bounty purposes and aims to provide assistance for recon, static code analysis and exploits using ADB and JADX.
-
kali-opencode-usbgithub.com/Adarsh1Y/kali-opencode-usbupdated this year
Bootable Kali Linux USB with AI-powered pentesting: OpenCode, CLI Agent, Kali MCP (35+ tools), and Shannon Plugin (autonomous pentesting with 600+ Docker tools). Boot anywhere, pentest everything, leave no trace.
MIT ★ 16 -
Local-first AI security & pentesting platform via MCP — Rust static scanner + Python MCP server with WSTG playbooks, RBAC/IDOR matrix & SARIF export.
MIT -
kali_mcpgithub.com/0x7556/kali_mcpupdated this year
Kali AI Pentest MCP tools 渗透测试工具集
★ 70 -
AI-driven Kali pentesting over MCP — Streamable HTTP server + LLM agent client (nmap, gobuster, nikto, sqlmap, …)
MIT ★ 2 -
⚔️ Autonomous red-team swarm for AI apps, agents & MCP servers — pentest your agent before someone else does.
Apache-2.0 ★ 2 -
Secure, modular MCP server wrapping nmap, nuclei, gobuster, subfinder, httpx, nikto, sqlmap for AI-powered pentesting
MIT ★ 1 -
hacktricks-mcp-servergithub.com/Xplo8E/hacktricks-mcp-serverupdated this year
Bring HackTricks pentesting knowledge into Claude Desktop. Search 1000+ security techniques, exploits, and payloads without leaving your AI assistant. MCP-powered, npx-ready.
go MIT ★ 11 -
AI black-box pentest agent. Claude Code Skill (wave-driven recon) + MCP Server (asset store, 5-layer vuln gate, auto-resume).
MIT -
Connect Claude Code or Cursor to PreHack, the autonomous AI pentester. Device-code login, no API key.
Apache-2.0 -
gorigithub.com/hahwul/goriactive
A fast, keyboard-driven HTTP intercepting proxy and pentesting toolkit for the terminal built for humans and AI agents alike.
go Apache-2.0 ★ 138 -
MCP (stdio JSON-RPC) server for Pentool AI — local LLM assistant for pentest: pick checks, bypass WAF, find endpoints. Made for DrXOps/pentool.
NOASSERTION ★ 1 -
nockgithub.com/jessn-dev/nockupdated this year
AI-aware command launcher for pentesters: fuzzy-search your command arsenal, auto-fill target variables, and expose it to AI agents over MCP. Single Go binary, provider-agnostic, works offline.
Apache-2.0 -
AI Pentesting Framework, Bug Bounty MCP Server, SAST/DAST Taint Engine & 12 Offensive Security Skills for Claude Code, Google Antigravity, Codex & Cursor.
MIT ★ 7 -
MCP wrapper for Burp Suite that builds complete, well-formed HTTP requests from structured input + ingests dedup/JS exports for token-thrifty AI-assisted pentesting. Bundles a fixed Burp extension.
MIT ★ 7 -
Authorized Android pentest lab, drivable by hand or by AI — Frida bypass chain, live traffic capture with automatic IDOR flagging, full MCP control plane, web dashboard.
MIT ★ 9 -
Vibe code fast. Ship like an engineer. AI engineering framework packaged as an MCP server that enforces TDD, security scanning, pentesting, secret management, QA audits, and deployment to a securely configured VPS — automated with up to 100× fewer exploration tokens.
MIT ★ 11 -
AutoPentest-MCPgithub.com/aamirizwann/AutoPentest-MCPupdated this year
Autonomous-pentest MCP server — one-command install of 140+ security tools (Pentest-MCP + HexStrike + MobSF) with auto-wired AI clients (Claude Code, Gemini CLI, OpenAI, DeepSeek, Ollama).
NOASSERTION ★ 2 -
mergen-mcpgithub.com/g4sk0/mergen-mcpupdated this year
Mergen is an MCP server that gives your AI a real red team brain. It doesn't just run tools, it picks the right ones, chains them together, and actually makes sense of the output. Built by pentesters, for pentesters who are tired of babysitting scripts.
MIT ★ 17 -
redact-mcpgithub.com/r3352/redact-mcpupdated this year
MCP server that auto-obfuscates sensitive data so Claude never sees real client data during pentesting. Regex + AI-powered NER detection.
npm ★ 6 -
Jikida — the security toolkit for modern and AI-built web apps: pentest, code & repo scanning, a managed WAF, and an MCP server for AI editors.
npm Apache-2.0 ★ 2 -
MCP server exposing a pentest toolkit to AI assistants. Python, Docker. Kali Linux
MIT -
contextsgithub.com/Rifteo/contextsupdated this year
Security engagement contexts for AI agents - load the right knowledge base before starting a pentest or audit. Served via MCP through rifteo-context-mcp.
MIT -
A systematic, AI-powered penetration testing reasoning engine (MCP server) for attack path planning, CTF/HTB solving, and automated pentest workflows. Features Beam Search, MCTS, attack step scoring, and tool recommendations.
MIT ★ 38 -
A systematic, AI-powered penetration testing reasoning engine (MCP server) for attack path planning, CTF/HTB solving, and automated pentest workflows. Features Beam Search, MCTS, attack step scoring, and tool recommendations.
MIT -
⚡ Autonomous AI Interception Proxy, Multi-Protocol OAST Canary Engine & Attack Hypothesis Ledger for LLM Pentesting Agents (Claude Code, Cursor, OpenCode, Hermes)
-
Standalone MCP server for Darkmoon (@darkmoon_ai/mcp-server): run_pentest/get_run_status/list_campaigns/get_findings over stdio. Requires a Darkmoon Pro endpoint; engine+CLI are OSS (GPL-3.0).
npm GPL-3.0 ★ 1 -
AI network analysis toolkit + MCP server for authorized pentesting: Wireshark/tshark capture, credential extraction, threat intel, Nmap scanning. | 面向授权渗透测试的 AI 网络分析工具库 + MCP Server
MIT -
All-in-one security testing toolbox that brings together popular open source tools through a single MCP interface. Connected to an AI agent, it enables tasks like pentesting, bug bounty hunting, threat hunting, and more.
MIT ★ 219 -
Deception-layer honeypot that captures & reverse-controls AI pentest agents — embedded decoys, prompt-injection counter-offense, MCP honeypot, conversational C2.
AGPL-3.0 ★ 181 -
AI-powered pentesting automation with MCP integration for Claude Code - parallel scanning, OWASP ASVS 5.0, workflow recording/replay
NOASSERTION ★ 1 -
CYBERDUDEBIVASH® MCP Server – Zero-Trust AI Cybersecurity Command Center (Private Development) Production-grade autonomous AI agents for SOC, pentesting, malware analysis, threat intel & DevSecOps. © 2026 CYBERDUDEBIVASH – All Rights Reserved
NOASSERTION -
HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.
★ 1 -
🛡️ 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 -
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 -
hexstrike-aigithub.com/0x4m4/hexstrike-aiupdated this year
HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.
MIT ★ 13,615 -
Open-source, self-hostable backend-as-a-service — a Supabase × Firebase hybrid on your own free Oracle Autonomous AI DB. Auth with cookie sessions, auto REST tables, RLS, realtime, storage, webhooks, SQL console, MCP server, transactional email (Resend/SMTP/OCI) — 82-check self-hack pentest ships in-repo.
Apache-2.0 ★ 1 -
nobody-pentest-ultraupdated this year
150+ security tools MCP server with AI-powered analysis for Claude Code, GPT, Copilot, etc.
pypi MIT -
Pentest-MCP-Servergithub.com/thirukguru/Pentest-MCP-Serverupdated this year
MCP for pentest tools
-
MCP server with YouTube transcripts, FREE multi-language translation, and AgentFold analysis
npm MIT -
Advanced Model Context Protocol (MCP) server for browser automation and penetration testing tools.
npm MIT -
Pentest-MCPgithub.com/Vasanthadithya-mundrathi/Pentest-MCPupdated this year
🐉 Autonomous Penetration Testing Agent powered by MCP (Model Context Protocol) with Kali Linux and HexStrike AI integration. Exposes 150+ security tools to AI assistants for intelligent vulnerability assessment.
★ 10 -
OSCP+ and OSWE pentest knowledge base for CLI agents and humans: 70 structured modules, section-level retrieval CLI, attack-path graph, and a stdlib-only MCP server.
MIT ★ 1 -
A Docker-based Model Context Protocol (MCP) bridge that enables AI-assisted, controlled access to penetration testing tools on Kali Linux systems through secure remote command execution.
-
mcp-api-pentestgithub.com/josenieto/mcp-api-pentestupdated this year
MCP server for autonomous API logic penetration testing. AI-driven detection of OWASP API Top 10 vulnerabilities (BOLA/IDOR) via multi-session authorization comparison. Supports Bearer, Basic, API Key, Cookie auth. Generates Markdown security audit reports with evidence.
MIT ★ 1