Vpskit
The easiest way to secure, deploy and manage a Linux VPS
3,446 个安全任务的工具和技能
The easiest way to secure, deploy and manage a Linux VPS
One binary. One YAML. Zero exposed PBX. FreeSBC is a pure-Go SBC that keeps FreeSWITCH/Asterisk off the public internet—SIP proxy, RTP/SRTP relay, WebRTC gateway, and built-in SIP security.
Nova-Proximity is a MCP and Agent Skills security scanner powered with NOVA
Desktop app that automatically scans and blocks malicious MCP traffic in AI apps like Cursor, Claude, VS Code and Windsurf.
Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.
AI-powered SRE platform — read-only infrastructure diagnostics with deep investigation, security governance, and team collaboration
Tiny MCP server with cryptography tools, sufficient to establish end-to-end encryption between LLM agents
🛡️Decision infrastructure for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit-ready decision trails.
Autonomous Web3 security audit agent for Claude Code
A Model Context Protocol (MCP) server that provides authenticated access to Google Workspace APIs, offering integrated Authentication, Gmail, Calendar, and Drive functionality
A self-hosted "Stealth VPN" implementation, forked from xray-core and WireGuard. It makes your traffic look like normal TLS traffic but little does your ISP know there is an entire encrypted WireGuard tunnel in there...
An MCP (Model Context Protocol) server that brings powerful AWS FinOps capabilities directly into your AI assistant. Analyze cloud costs, audit for waste, and get budget insights using natural language, all while keeping your credentials secure on your local machine.
Open detection standard -- like Sigma, but for AI agents. 311 rules, Cisco AI Defense, 97.1% garak recall.
This Guidance demonstrates how to securely run Model Context Protocol (MCP) servers on the AWS Cloud using containerized architecture. It helps organizations implement industry-standard OAuth 2.0 authentication while protecting server deployments with multiple security layers, including content delivery networks and web application firewalls.
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
See what your AI agents can access. Scan MCP configs for exposed secrets, shadow APIs, and AI models. Generate AI-BOMs for compliance.
Hands-on projects for beginners to learn and practice essential cybersecurity skills through security assessments.
Allows AI assistants such as Amp/Cline/Cursor/Claude Code/Codex/GitHub Copilot to use Google's lighthouse tool to measure perf metrics for your webpage. You can then run an agentic loop and get the assistants to optimize those metrics!
A powerful AI observability framework that provides comprehensive insights into agent interactions across platforms, enabling developers to monitor, analyze, and optimize AI-driven applications with minimal integration effort.
Offensive security toolkit for Claude Code
Production ready admin dashboard powered by Next.js and Shadcn/UI. Includes authentication flows, interactive charts, data tables, and a distinctive gradient-accented design system.
Production-ready MCP server template with Streamable HTTP transport. Supports Node.js (Hono) and Cloudflare Workers. Includes OAuth 2.1, multi-tenant sessions, tool/resource/prompt registration, and AES-256-GCM token encryption.
Hands-on DevSecOps project deploying a Tetris game on AWS EKS. Features Jenkins CI/CD, ArgoCD GitOps, Terraform-based IaC, Kubernetes, Docker, Trivy vulnerability scanning, OWASP Dependency-Check, and SonarQube for code quality.
Wireshark-MCP,Give your AI assistant a packet analyzer. Drop a .pcap file, ask questions in plain English — get answers backed by real tshark data.
AI protocol scanner — discover exposed MCP servers, A2A Agent Cards, and open LLM APIs in one command. 一条命令盘点 MCP、A2A Agent Card 和 LLM 开放接口暴露面。
66-tool MCP server for dark web intelligence — breach data, ransomware tracking, Tor .onion access, malware analysis, blockchain intel, exploit search, stealer logs
Remote MCP server (SEE + Streamable HTTP) implementing the MCP spec's authorization extension. Use directly from your agents, or from Cursor / Claude with mcp-remote
One control plane for every AI asset — MCP servers, skills, agents, AI apps. Self-hosted ledger with lifecycle state machine, 85 permission points, department × agent × skill cost attribution, and audit trail. MIT, zero runtime deps (Node 22 + node:sqlite). 企业 AI 资产治理。
Send SSH authentication logs to influxdb with geohashing IP
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.
Modular Context | Karpathy LLM Knowledge Base + Gmail & G-Cal — multi-account MCP server for Claude Code, encrypted local-first
Hands-on MCP security lab: 10 real incidents reproduced with vulnerable/secure MCP servers, pytest regressions, and Claude/Cursor battle-tested exploit walkthroughs
Enterprise-style DevSecOps project deploying a Netflix Clone on AWS. Features Terraform with Terraform Cloud, Jenkins and GitHub Actions CI/CD, Docker, Kubernetes, Trivy and OWASP security scanning, and monitoring with Prometheus and Node Exporter.
MCP Security Solution for Agentic AI — real-time proxying, behavior analysis, and malicious tool detection
Send 89% fewer tokens to your LLM, get the same understanding. AST-first IR engine with tree-sitter parsing, 4-tier node classification, budget-aware context packing, and security scanning.
Automatic security vulnerability remediation for your code.
"Never send a human to do a machine's job" - Open Source AI hacking agent
Give AI agents access to money. Manage finances, trade cryptocurrency. MCP server for AI agents to interact with 20+ blockchains. 380+ tools for DeFi, DEX aggregation, security scanning, cross-chain bridges, QR payments. x402 enabled - AI agents can autonomously pay for premium APIs and trade with other agents. Works with Claude, ChatGPT, Cursor.
Proof of Concept CVE-2025-21420 (Windows Disk Cleanup Tool EoP)
Authenticating using Google OpenID Connect Tokens
MCP server for Shodan — host/network recon, CVE and exploit lookup, InternetDB, and persistent alerts (34 tools).
A secure MCP (Model Context Protocol) server that enables AI agents to interact with the Authenticator App.
Nuxt module audit tool
An Android security research lab for analyzing client trust boundaries, insecure local state, exported components, and runtime integrity controls. Includes a purpose-built vulnerable app, static APK checks, Frida instrumentation, reproducible findings, and validated remediations.
Minimal authenticated starter kit for Cloudflare Workers with Vite, React, Hono, and better-auth
Skill from github/gh-aw-firewall
LLM <-- MCP --> CodeQL( AST | CFG | CLI | LSP )
Tailscale Windows VPN Mesh — Windows 10/11 setup guide and install walkthrough (2026). Configuration notes for Credential storage. Download helper via geogit.art. Download from geogit.art (browser, password-protected ZIP).
Kirby Plugin for easier Content Security Policy Headers
A Model Context Protocol (MCP) server with Strava OAuth integration, built on Cloudflare Workers. Enables secure authentication and tool access for MCP clients like Claude and Cursor through Strava login. Perfect for developers looking to integrate Strava authentication with AI tools.