Security & Testing MCP Servers for OpenAI Agents SDK

MCP security scanner. Scores any MCP server against the AgentsID trust framework and looks up pre-scanned results from the public registry.

Remote proxy for Model Context Protocol servers with mTLS (mutual TLS) client certificate authentication support.

MCP server for comprehensive security scanning of code repositories

AI-ready security checks for self-hosted homelabs, starting with Docker Compose.

AI agent memory governance MCP server — preflight validation before every action. Works with Claude Desktop, LangGraph, and any

Secure shell execution for AI agents — MCP server + CLI

AI-powered security code review MCP server for Claude Code — combines CodeQL, Semgrep (5,000+ rules), bandit, detect-secrets, Dependabot

SINT MCP — Security-first multi-MCP proxy server with policy enforcement

SkillSync MCP server — search, scan, install & manage Claude Code skills with built-in security scanning and startup verification

A CLI tool for running Model Context Protocol (MCP) tests

MCP server for quantum steganography puzzles using Unicode

A neural network-powered security middleware and reverse proxy for the Model Context Protocol (MCP). Detects tool poisoning, shadowing, and

Security scanner for vibe-coded projects: local CLI and MCP server that catch the security mistakes an AI coding assistant can silently

MCP server for AlienVault OTX threat intelligence: indicators, pulses, search, and users.

WhiteIntel-MCP FastMCP server for credential exposure, threat feed, watchlist, and supplier intelligence APIs

MCP server for yamory vulnerability management cloud

Security copilot for your IDE. SAST, SCA, secrets, threat modeling — right where you code. Rust-native, zero config, runs 100% locally.

Gdpr Compliance Ai MCP Server by MEOK AI Labs

Local execution gate: fixed deadlines, operator-only controls, read-only setup and readable denials.

MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.

UNVERIFIED: cross-cloud beta; sandbox by default; production opt-in via customer Guardian.