Search

Standalone MCP client for the hosted PerfAI cloud API — register an app by URL, run a security test, pull findings, and get fix prompts from Claude Code, Cursor, or any MCP client.

LokinSkills — Security scanner for AI agent skill files. Detects reverse shells, prompt injection, supply chain attacks, MCP config risks and more. 78+ heuristic rules, no account required.

Security scanner for Model Context Protocol (MCP) servers. Audits running servers against the OWASP MCP Top 10 and outputs console, JSON, and SARIF reports. Runs as a CLI or as an MCP server itself.

jwt-lab – A fast, secure, beautiful JWT CLI tool and MCP server for developers & AI agents. Encode, decode, verify, inspect, audit, and generate keys for JSON Web Tokens.

MCP server for SkillsSafe — AI agent skill security scanner. Detects prompt injection, credential theft, zero-width character attacks, and ClawHavoc malware. Free, no API key required.

The largest Claude Code plugin marketplace. 500 plugins, 600+ developer tools in one MCP server. Security, testing, DevOps, databases, frontend, backend, ML/AI, mobile, cloud, and more.

The CI quality gate for MCP servers — functional tests + official conformance + OWASP-MCP-Top-10 security in one command, with SARIF, a 0-100 safety score, and a README badge.

Zero-code runtime observability for JS/Python + AI agent debugging. Traces LangChain, CrewAI, OpenAI, Anthropic, Gemini. Eval, security, compliance, cost tracking. Free, local-first.

Agent-driven ML researcher in a secure, reproducible KVM lab: five standalone scientific-state MCP servers within per-user VMs with driver / trusted / hostile zone isolation

Microsoft 365 tenant security posture scanner for Claude / Copilot / AI-agent deployments. Runs locally via MSAL device-code flow — never touches your credentials or tenant data.

Secure AI Adapters for OpenAI, Claude, LangChain, LiteLLM (100+ providers), MCP, and MCP Proxy (inline gateway). Note: mcp-proxy and litellm extras require Python 3.10+

🌟 Open Source AI Agent Security Infrastructure — intercepts and blocks dangerous agent behaviors before they happen. Just one command! Join us to build safer Human-AI Symbiosis!

One command. Full stack. Zero compromise. — All-in-one Claude Code skill with 4-layer security, triple verification, and compact defense. Build, fix, clean, deploy, review with /aura.

Static production-readiness auditor for Flask apps: architecture, templates, deployment, testing, security, database, dependencies and code quality. CLI, pre-commit hook, GitHub Action and MCP server.

The security standard for MCP and AI agents. 141 detection patterns, CORTEX threat intelligence, pre-deployment audit, intent firewall, flight recorder, and 390+ exports. Zero dependencies, runs locally.

🚀 Ultimate Developer Productivity Suite - 11 specialized MCP servers for AI-powered code analysis, security scanning, browser automation, and workflow orchestration. FastAPI + React + TypeScript + Docker ready.

Shared scaffolding for the DecodingTrust-Agent (DTAP) superred targets: the agent-agnostic Target base, the security-domain forest, controllables/observables, env/MCP/Docker lifecycle, and the byte-faithful judge runner.

Operating System for your personal AI Agents with Security-first approach. Multi-channel (WhatsApp, Telegram, Discord, Slack, iMessage), multi-provider (Claude, GPT, Gemini, Ollama), fully self-hosted.

The Security & Cost Control Layer for AI Agents — Guard, Shield, and Sentinel tiers: budget control, per-agent credential isolation, OAuth scope enforcement, MCP policy enforcement, and compliance reporting.

Model Context Protocol (MCP) server exposing the XploitScan security scanner as a tool Claude, Cursor, and other MCP clients can call. Scan AI-generated code from inside your AI coding agent.