Search

ChatGPT ↔ local Codex Agent bridge | Windows Control Center + macOS browser-host preview. MCP server / user-owned Secure Tunnel / 中文安装配置与使用教程。Community software, not an official OpenAI product.

Runtime security for AI agent sandboxes. Drop-in protection against prompt injection, secret exfiltration, and sandbox escape — works with [Vercel](https://vercel.com/sandbox), [E2B](https://e2b.dev/), [Daytona](https://www.daytona.io/), [Cloudflare Conta

AI model: sushitrash26/Qwen-Security-Agent-3B (text-generation)

This project develops an Agent Security MCP Gateway, a fail-closed reference monitor placed between an MCP host and downstream tool servers.

My project develops an Agent Security MCP Gateway, a fail-closed reference monitor placed between an MCP host and downstream tool servers.

A Model Context Protocol (MCP) server that provides security functionality for AI agents, focusing on detecting and redacting sensitive information in text content.

AI Space: Agents-MCP-Hackathon/pypi-security-audit-local-mcp

AI Agent Security: Otonom yapay zeka ajanlarının ve MCP protokolünün güvenlik riskleri. Excessive Agency, tool poisoning ve Meta'nın "İki Kural" (Rule of Two) savunma çerçevesi.

A security gateway that sits between AI agents and MCP tool servers, enforcing per-role authorization, JSON-schema validation, and least-privilege tool scoping — so an agent only ever sees and calls what its role permits, with no way to bypass the check.

AI model: AI4SWEng/kio12-security-agent-gemma4-12b-v2

AI model: Disdang/Meta-Plasm-v8.0-MCP-Secure

AI model: AI4SWEng/kio12-security-agent-qwen35-9b-v2

AI model: AI4SWEng/kio12-security-agent-qwen25-coder-7b-v2

Scanner engine for the agentic-security Claude Code plugin — SAST, SCA (function-level reachability + CISA KEV), secrets, IaC, prompt-injection, MCP/agent-tool audit, auth/authZ deep analysis, attack chains, PoC generation, business logic, toxic-combinati

AI model: AI4SWEng/kio12-security-agent-ministral3-8b-reasoning-2512-v2

AI model: AI4SWEng/kio12-security-agent-foundation-sec-8b-reasoning-v2

AI model: AI4SWEng/kio12-security-agent-eurollm-9b-instruct-2512-v2

Exploit-then-defend security workshop: a deliberately vulnerable Quarkus + LangChain4j conference assistant (agent + MCP server) hardened across four OWASP LLM topics.

Redis-based rate limiting for AI agent platforms with trust and penalty multipliers

IAST agent