Best Security & Compliance Agents

The most powerful Android RPA agent framework, next generation of mobile automation robots.

A secure low code honeypot framework, leveraging AI for System Virtualization.

ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.

A security scanner for your LLM agentic workflows

MCP configuration to connect AI agent to a Linux machine.

🔥🔒 Awesome MCP (Model Context Protocol) Security 🖥️

MCP for Security: A collection of Model Context Protocol servers for popular security tools like SQLMap, FFUF, NMAP, Masscan and more. Integrate security testing and penetration testing into AI workfl

A growing collection of MCP servers bringing offensive security tools to AI assistants. Nmap, Ghidra, Nuclei, SQLMap, Hashcat and more.

The open-source execution engine for AI agents. 412 modules, MCP-native, triggers, queue, versioning, metering.

High-precision Python SAST & Dead Code Remover. Finds unused functions, secrets, and security flaws with hybrid static analysis + local LLM agents. Privacy-first & low noise. MCP server for SAST too.

MCP server that connects AI assistants to HackerOne for bug bounty hunting

See what your AI agents can access. Scan MCP configs for exposed secrets, shadow APIs, and AI models. Generate AI-BOMs for compliance.

Reticle intercepts, visualizes, and profiles JSON-RPC traffic between your LLM and MCP servers in real-time, with zero latency overhead. Stop debugging blind. Start seeing everything.

Supercharge AI Agents, Safely

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

A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

MCP server for Shodan — search internet-connected devices, IP reconnaissance, DNS lookups, and CVE/CPE vulnerability intelligence. Works with Claude Code, Codex, Gemini CLI, and Claude Desktop.

ToolHive is an application that allows you to install, manage and run MCP servers and connect them to AI agents

MCP server for Slither static analysis of Solidity smart contracts

Security scanner for AI agent skills & MCP servers. 173 detection rules. 13 categories. 5 registries monitored daily. OpenClaw detection included. No API keys, no cloud, no LLM. One binary. Detection

A powerful MCP (Model Context Protocol) Server that audits npm package dependencies for security vulnerabilities. Built with remote npm registry integration for real-time security checks.

MCP server for VirusTotal API — analyze URLs, files, IPs, and domains with comprehensive security reports, relationship analysis, and pagination support.

MCP Checkpoint continuously secures and monitors Model Context Protocol operations through static and dynamic scans, revealing hidden risks in agent-to-tool communications.

Asterisk Model Context Protocol (MCP) server.

Secure ChromeMCP Server - Query and Debugging sites using Google Chrome with additional security hardening layers

Autonomous Penetration Testing AI Agent

AgenticMail Enterprise — cloud-hosted AI agent identity, email, auth & compliance for organizations

TypeScript package for AppSec AI Agent management

AI-native quality gate engine with local Bayesian learning. AST analysis, drift detection, Fix Packet generation, and agent self-healing across TypeScript, JavaScript, Python, Go, Ruby, and C#.

Universal AI agent framework for your terminal. 22 specialist agents, 262 tools, 20 providers. Game dev tools (8 engines, ECS, physics, netcode, levels, particles, shaders, sprites). Programmatic SDK,

Cryptographic security layer for AI agents. Ed25519 identity, signed messages, trust scoring. Works with LangChain, CrewAI, AutoGen, OpenClaw, or any agent framework.

MVA (Model-View-Agent) framework for the Model Context Protocol. Structured perception packages with Presenters, cognitive guardrails, self-healing errors, action consolidation, and tRPC-style type sa

MCP server for The Insumer Model — read-first blockchain verification infrastructure that returns ECDSA-signed, privacy-preserving booleans across 32 chains without exposing wallet balances. 26 tools:

Anthropic Sandbox Runtime (ASRT) - A general-purpose tool for wrapping security boundaries around arbitrary processes

Prompt injection defense framework for AI tool-calling

Minimal Clawdstrike tool wrappers for LangChain tools

Security scanner for AI agent skill files

New Relic Security Agent for Node.js

Zero-dependency autonomous AI agent. Code, browse, search, automate. Works with any LLM — Ollama, Claude, GPT, Gemini, DeepSeek, Groq, Mistral, Grok.

Claude Code autonomous agent manager - A web UI for managing Claude Code agents

x402 Payment Firewall SDK - On-chain security for autonomous agent payments on Cronos

Structured pentest engagement memory for the Nyx autonomous agent

Security by design CLI for AI-assisted development - scans projects and guards autonomous agent runs

AI agent framework with defense-in-depth security, multi-agent orchestration, and provider abstraction

Zentinel Agent SDK for TypeScript - v1 and v2 protocol support

Governance-first agent SDK with deterministic policy gates, auditable run records, and IoC-oriented orchestration.

OpenCode plugin that sandboxes agent commands using @anthropic-ai/sandbox-runtime (seatbelt on macOS, bubblewrap on Linux)

Deterministic action verification for LLM agent security

TypeScript-based AI agent framework with native LLM integration, workflows, and 15+ built-in integrations (Development Preview)

Skills Guard Core - Security Scanner Engine for Anthropic Agent Skills