Every AI skill, independently scanned. Public, open-source trust scoring for skills, MCP servers, hooks, and plugins across every agent platform. Apache-2.0. saferskills.ai
Java decompiler MCP server for AI coding agents. Explore, search, and decompile JAR, WAR, EAR, and AAR bytecode with CFR, Vineflower, or Procyon.
MCP server, standalone CLI, and extension orchestrator
DNS and email security scanner with 82 MCP tools for SPF, DMARC, DNSSEC, SSL, and brand audits.
MCP server for Shodan — host/network recon, CVE and exploit lookup, InternetDB, and persistent ...
Agentless, read-only security audit of Linux servers over SSH. Ranks what to patch first: CVEs with KEV and EPSS, SSH access, exposed ports, host health, with rollback-ready fixes. Terminal UI (TUI),
Discover and audit MCP servers for security vulnerabilities across Claude Code, Cursor, VS Code, and more
Give AI agents a real Chrome/Firefox browser through MCP. Human-approved automation, API reverse engineering, OpenAPI generation and reusable workflows. Local-first.
Open-source, self-hosted, versioned vault for AI-generated HTML, Markdown, Mermaid, and image artifacts, with scoped MCP access and isolated two-origin previews.
A playground for Model Context Protocol (MCP) server built with TypeScript and Streamable HTTP transport with an OAuth Proxy for 3rd party authorization servers like Auth0
GenPark Ctrip Hotel Corporate Policy Compliance Auditor - Automates enterprise travel policy validation, rate parity audits, and carbon ESG compliance.
Secure local REST, CLI, MCP, and agent bridge for IDA Pro 9.x
Security-guarded MCP server for Bugzilla, written in Rust
GenPark Ctrip Hotel Corporate Policy Compliance Auditor - Automates enterprise travel policy validation, rate parity audits, and carbon ESG compliance.
Self-hosted bridge to Omnivox (Quebec CEGEP portal): MCP server, REST tool gateway with OpenAPI spec, Omnivox API proxy, and reverse-engineered API docs
RavensPort is an MCP proxy in your tray on 127.0.0.1. Each agent gets one endpoint with exactly the tools you granted, from any MCP servers and APIs, and call filters stop secrets, personal data and r
Read-only MCP server for Trino: each query runs as the user who asked, and Trino's access control decides what they see. Nine tools, writes refused on the SQL tree, bounded SQL, rows, bytes and time.
Foundgine lets callers express intent while your application decides what's allowed, safe, and executed
Secure, scoped filesystem MCP server for ChatGPT and other MCP clients — read-only by default, with controlled mutations, binary transfer, native Codex/Claude/Qoder runtimes, generic ACP v1 profiles,
AI agent & MCP trust registry — independent, evidence-based trust scores for 1.3K+ open-source AI agents and MCP servers. Runtime-trust calibrated (MCP, dependencies, provenance drift), with side-by-s
Run FiveM resources (Lua, JavaScript and NUI) in your browser and in CI. No GTA V, no server, no restarts.
Agent 自主渗透测试工具: SPA/MPA 接口枚举、运行时流量捕获、权限树还原、参数矩阵合并。
REA reverse-engineering MCP server in Docker, with JADX, Apktool and adb for APKs.
A secure, highly capable MCP server written in Rust. It exposes a comprehensive suite of filesystem operations as tools for AI agents.
Autonomous headless Ghidra 12 reverse engineering for Pi, omp, and MCP clients: decompile, xrefs, call graphs, strings, memory, and patches without the GUI.
A secure JavaScript sandbox designed for safe AI agent code execution. Protects against code injection, prototype pollution, and sandbox escapes. The security layer that makes AI-generated code safe t
The policy layer for AI coding agents. aiZee governs what Cursor, Claude Code, Copilot, Windsurf, Devin & MCP agents may do — 139 enforcement gates, 29 personas, 245 skills, BMAD runtime, hybrid memor
REA (Reverse Engineer Anything) in Docker: Android APK decompilation with JADX, Apktool and adb built in, Ghidra on demand, behind a token-guarded Streamable HTTP MCP endpoint. Also stdio MCP and a CL
MCP-сервер для БДУ ФСТЭК (86 000+ российских уязвимостей). Поиск через SQLite FTS5 с фильтрами по CVSS/опасности/году/вендору, обратный маппинг CVE→БДУ. Обход геоблока через GitHub-зеркало.
218 silent contract changes found in the npm MCP top. Pin MCP tool contracts, fail CI on drift. Zero deps, no telemetry, on-chain verified.
MAWYXX PRIME — The Ultimate AI Architecture Constitution & System Prompt for Cursor, Windsurf, and Copilot. Zero-Trust AI coding standard for production-grade AI agents.
Kerberos/SPNEGO single sign-on for MCP servers in FreeIPA environments. Provisioning framework for Windows (via WSL), Linux and macOS development environments.
Kali-MCP is an MCP server that connects AI agents to Kali Linux penetration testing tools.
Open source regime-adaptive financial analysis engine with MCP tool orchestration. Apache 2.0 licensed with defensive patent grant.
With Pocket ID, you can protect your MCP server with OAuth 2.1 and OpenID Connect. This demo shows how quickly OAuth can be added to an MCP server with Pocket ID.
A security graph reporting tool, with agentic workflows, AI chat assistant, and automation for CVE remediation and graph data population.