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.
-
hand-crafted cybersecurity tools. made by me and aa certain LLM. made to be usable by humans and AI agents through an MCP server, that comes packed with the repo.
-
🔌 Exposes cybersecurity over MCP — AI-powered automation tool. MIT.
go MIT -
FindEvil-CyberSecuritygithub.com/kostasuser01gr/FindEvil-CyberSecurityupdated this year
🏆 Hackathon — AI-powered threat detection & malicious pattern recognition tool for cybersecurity analysis
MIT -
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 -
cyberjobsactive
Find open cybersecurity jobs with stated salaries from a terminal or from Node, and give MCP clients the CyberJobs.cc tools over stdio.
npm MIT -
Multi-Agent Autonomous Cybersecurity Platform (Go + LLM) — layered agent orchestration, 91 YAML tool recipes + 50+ built-in MCP tools, HITL safety, single-binary offline deployment.
MIT -
secai - agentic cybersecurity engine: 272 capability scripts (93 detection skills + 176 tools, 121 ported from 995 concepts), Rust core + one contract, MCP, offline-first triage. No proof, no report.
NOASSERTION ★ 1 -
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 -
MCP server for the Nozom Cybersecurity GRC Platform — exposes GRC API endpoints as Model Context Protocol tools. R-EXTSPEC: @modelcontextprotocol/sdk v1.29.0 — https://modelcontextprotocol.io/specification/latest
npm MIT -
FYP-XploitEye-Web-and-System-Vulnerabilities-using-Agents-LLMs-github.com/shoaib1522/FYP-XploitEye-Web-and-System-Vulnerabilities-using-Agents-LLMs-updated this year
XploitEye is a state-of-the-art, AI-powered multi-agent cybersecurity platform designed to automate the complete Cyber Kill Chain. By orchestrating advanced Large Language Models (LLMs) and industry-standard security tools, XploitEye provides a unified interface for both Red Team (Offensive) and Blue Team (Defensive) operations.
-
Zantrixgithub.com/ankitk090-lang/Zantrixupdated this year
A Model Context Protocol (MCP) server that provides basic cybersecurity diagnostic tools.
ISC -
kali-mcp-servergithub.com/Vasanthadithya-mundrathi/kali-mcp-serverupdated this year
Kali MCP Server - Powerful MCP server providing Docker-based access to Kali Linux penetration testing tools with 26 specialized cybersecurity utilities
★ 1 -
Pentest-MCPgithub.com/AnGrY-Althaf/Pentest-MCPupdated this year
A Model Context Protocol (MCP) server that provides educational penetration testing capabilities through a secure Docker container running Kali Linux tools. Designed for authorized security testing and cybersecurity education.
NOASSERTION -
A lightweight, extensible cybersecurity toolkit that connects AI assistants to security tools through the Model Context Protocol (MCP), enabling AI-assisted security research, scanning, and analysis.
MIT ★ 13 -
🔌 Exposes EU Cyber Resilience Act (CRA, Reg 2024/2847) compliance over MCP — 5 tools, 13 tests. Annex I cybersecurity, Art 10 vuln handling, Art 13 conformity assessment, SBOM. NIS2 crosswalk. By MEOK AI Labs.
pypi MIT -
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 -
CyberSecurity-MCPsgithub.com/secmate-ai/CyberSecurity-MCPsupdated this year
Model Context Protocol Server For Cyber Security
★ 18 -
Autonomous Security Assessment, Threat Intelligence Triage & SOC Investigation Workbench with Cryptographic Choke Points
MIT -
operant-mcpgithub.com/operantlabs/operant-mcpupdated this year
Turn your AI agent into a hacker by plugging in this MCP
MIT ★ 27 -
Cybersecurity-MCPgithub.com/LiamTCollins/Cybersecurity-MCPupdated this year
A tool to add to an agent's repertoire to improve security of AI created apps and sites.
Apache-2.0 -
cybersecurity-intelligence-mcpgithub.com/apifyforge/cybersecurity-intelligence-mcpupdated this year
Cybersecurity intelligence for AI agents — search 200,000+ CVEs, check the CISA Known Exploited Vulnerabilities catalog, enumerate subdomains via Certificate Transparency, audit DNS and email security, scan internet-exposed hosts via Censys, and investigate domain registration — all through a single MCP server.
MIT ★ 1 -
Pentest-MCP-Servergithub.com/thirukguru/Pentest-MCP-Serverupdated this year
MCP for pentest tools
-
Cybersecurity warehouse system utilizing three agents that analyze the OT network for anomalies, ranks vulnerability fixes and catches spoofing. The orchestrator agent pulls those three agents into a single alert and maps each event to a MITRE ATT&CK for ICS technique ID.
NOASSERTION ★ 1 -
Self-contained MCP security server that scores AI agent tool-calls with a rule-based library + behavioral detector, giving explainable, MITRE-mapped verdicts for known attacks
MIT -
supremegithub.com/silence-codes/supremeupdated this year
World's First MCP-based code-security scanner
AGPL-3.0 ★ 2 -
lokis-mcpgithub.com/thpeng/lokis-mcpupdated this year
Lokis MCP Server will trick your LLM
MIT ★ 2 -
offensive-sec-mcpgithub.com/ans-inayat/offensive-sec-mcpupdated this year
offensive security ai mcp
NOASSERTION -
keelgithub.com/lutfizp/keelactive
Keel is the MCP control plane for authorized pentests and bug bounty. Plug it into Claude Code, Codex, Cursor, OpenCode, Hermes, Copilot, and any other MCP client. Keel runs scoped recon, keeps the target from getting hammered, and turns scanner noise into hunter-grade findings.
pypi MIT ★ 2 -
kali-mcp-servergithub.com/cyberillo/kali-mcp-serverupdated this year
A Python MCP Server that connects Large Language Models natively to a comprehensive suite of offensive security tools.
MIT ★ 11 -
MCP Security Review
pypi Apache-2.0 -
NeuralReapergithub.com/the-artist111/NeuralReaperupdated this year
AI-powered penetration testing framework with 55+ MCP tools, CVE intelligence, Active Directory, and autonomous security workflows.
MIT ★ 1 -
Provides agent chat for analysing Fiddler traffic using LLM models through MCP server and custom tools with robust python harness.
★ 10 -
Empowers the AI to perform penetration testing, vulnerability assessment, reconnaissance, and security reporting — all through natural language conversation.
MIT ★ 21 -
dfireballzgithub.com/valITino/dfireballzupdated this year
AI-native digital forensics & cybercrime investigation platform. 7 MCP servers (Volatility3, Ghidra, Wireshark, OSINT, threat-intel & more) orchestrated by Claude, ChatGPT, or Ollama — fully containerized, chain-of-custody enforced, court-admissible output.
MIT ★ 3 -
channel-toolsgithub.com/ChannelEngineer/channel-toolsupdated this year
—
-
A multi-agent AI cybersecurity system utilizing MCPs detecting cyberattacks against robots, PLCs, and industrial sensors in an AI-powered automated warehouse. Three detection agents watch network traffic, rank vulnerabilities via live CISA threat intelligence, and monitor robot command integrity. Orchestrator correlates alerts & tags each threat.
NOASSERTION -
🔎 Username, email & phone OSINT — 9,700+ lookup checks from 19 projects, with profile enrichment, bulk searches, evidence graphs and expert-reviewed updates.
pypi GPL-3.0 ★ 272 -
MCP server for RAG of web applications
MIT ★ 2 -
An Open Sourced Model Context Protocol (MCP) Local server that gives AI Clients real-time cybersecurity reconnaissance capabilities
pypi MIT ★ 29 -
AI-powered cybersecurity project featuring intelligent agents for security analysis, threat awareness, and exploring AI-driven security workflows.
MIT -
PocketRecon-AIgithub.com/hXR16F/PocketRecon-AIupdated this year
MCP Server for AI-powered security reconnaissance
MIT ★ 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 -
RedVector AI - AI-powered penetration testing and cybersecurity automation framework for security researchers and ethical hackers.
NOASSERTION ★ 47 -
Local security intelligence for CVE triage and remediation: risk scores from 46 data sources, fix plans for what you run, SBOMs in and out, and an MCP server with 42 tools for AI agents. Fleet mode watches every server from one place. Native Rust, private by default.
Apache-2.0 ★ 148 -
sqlmap-skynetgithub.com/drcrypterdotru/sqlmap-skynetupdated this year
SQLMap with Autonomous AI, phased workflows, RAG memory, and MCP Agent Tools
Apache-2.0 ★ 107 -
SpectreWeb-AIgithub.com/tuannguyen14/SpectreWeb-AIupdated this year
Self-Learning AI for Manual Web Penetration Testing
★ 14 -
mcp-sentinelgithub.com/jakeefr/mcp-sentinelupdated this year
Runtime security scanner for MCP tool poisoning. Native Claude Code plugin.
MIT ★ 3 -
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 -
birregithub.com/boecht/birreupdated this year
Model Context Protocol server for BitSight security ratings
pypi Unlicense -
Autonomous Offensive Security Agent for Red Team Operations
Apache-2.0 ★ 4 -
cybermcpgithub.com/mehmetaksy/cybermcpupdated this year
MCP server providing CVE lookup, IP geolocation, and file hash analysis tools for Claude — built with FastMCP
-
Token-optimized research engine & Agent Skill for 100% Open Access academic cybersecurity research (USENIX, NDSS, IACR, arXiv cs.CR, and NIST). Built for AI Agents & Security Analysts.
MIT -
pengstrike-mcpgithub.com/wangqiongpeng/pengstrike-mcpupdated this year
AI-Powered MCP Penetration Testing Framework - 150+ security tools with adaptive task model
MIT ★ 1 -
把「雲原生安全與基礎設施管理」和「AI/MCP 自動化滲透測試框架」合在同一個專案裡的統一平台,能及時(非回合制攻防)同時監控基礎設施跟防禦,和能自動讓 AI 調用工具去滲透該目標.
MIT ★ 4 -
Vexqr - Connect any AI (Claude, Gemini, Copilot, Cursor, etc.) to security tools with real-time supervision and MCP integration
MIT ★ 2 -
AntiStrike7.0github.com/xAmirHamza77/AntiStrike7.0updated this year
Antistrike 7.0 — Advanced AI-powered penetration testing platform with 99 attack modules, MCP integration, and web dashboard
★ 1 -
ghostkit-mcpgithub.com/pspray/ghostkit-mcpupdated this year
26 security tools for Claude, Cursor, and any MCP-compatible AI client. Powered by ghostkit.net.
-
Open-source AI cybersecurity harness to build & deploy continuous security agents that find, prove, fix and monitor vulnerabilities across code, binaries, dependencies, infrastructure. Web UI, CLI, CI and MCP.
Apache-2.0 ★ 1,371 -
Security-oriented Python tooling and CLI/MCP experiments for defensive research and developer workflows.
-
ssrfindgithub.com/cognis-digital/ssrfindupdated this year
Find SSRF-prone sinks and unvalidated URL fetches in code
NOASSERTION