Search

Governance & security control plane for Model Context Protocol (MCP) adoption: registry, gateway, policy engine, approvals, audit, and config scanner.

Local-first security scanner, MCP protocol inspector, dynamic fuzzer, sandbox runner, and report generator for Model Context Protocol servers.

LLM security middleware: prompt-injection detection, PII protection, tool policy, cost tracking. Python port of ai-shield-core.

LLM security middleware: prompt-injection detection, PII protection, tool policy, cost tracking. Python port of ai-shield-core.

📇 🏠 🍎 🪟 🐧 – A secure MCP (Model Context Protocol) server that enables AI agents to interact with the Authenticator App.

🐍 ☁️ - MCP server to access [Intruder](https://www.intruder.io/), helping you identify, understand, and fix security vulnerabilities in your infrastructure.

MCP Security Playground - Hack with MCP Servers, MCP Clients. Try out different vulnerabilities and abuse LLMs and agents in a UI friendly experimentation lab

Aran — a transparent security proxy for MCP stdio servers: blocks destructive tool calls and redacts prompt-injection payloads before they reach your agent or your machine.

🐍 ☁️ 🏠 - Security through absurdity: transforms SQL injection and XSS attempts into harmless comedy responses using AI-powered humor defense.

MCP server exposing a domain security & privacy checker (SSL/TLS, email auth, DNS, web headers). Local-first, zero telemetry.

Production-grade Model Context Protocol (MCP) security gateway with capability policy enforcement, multi-driver ephemeral sandboxing, and real-time inspector.

DryHack-MCP - an MCP server providing offensive-security tooling (curl, python, shell) and an AI-driven recommend_action engine for authorized penetration testing.

AI-powered agentic security scanner. Scan endpoints, audit packages, review source code. Autonomous agents discover, attack, verify, and report.

A deterministic second pair of eyes for AI-generated code — diff-aware, low-noise security review in your coding agent (MCP), editor, and CLI.

AI-powered OSINT agent, MCP server, and CLI. Interactive REPL + 30 tools. Anthropic Claude or local Ollama. For authorized security research use only.

Local, hardened autonomous security agent that tests a financial app and everything it trusts — AI/MCP, dependencies, and containers — with deterministically verified, cryptographically provable findings.

MCP server for Yoke domain intelligence — analyze domains across security, speed, DNS, SSL, email, and tech stack from any MCP-compatible AI client.

🦀 🏠 🚨 🍎 🪟 🐧 - A Rust-based MCP server to integrate Cortex, enabling observable analysis and automated security responses through AI.

MCP supply-chain security scanner: detect tool-poisoning, shadowing, hidden unicode, secret solicitation, and rug-pull drift in MCP servers before you install them.

AI-era threat modeling & repo scanning — OWASP-2026 aligned (LLM / Agentic / Data Security / MCP). Deterministic-first, zero-dependency core.