Search
clawsearch-guard
huacheng99
Pre-install & runtime security gate for AI agent skills — blocks dangerous skills and monitors tool calls
elasticsearch-mcp-vsee
michaellei2006
Secure MCP server for Elasticsearch integration with comprehensive tools (fork with hard-coded Elasticsearch indices and field names)
...moreforcefield
Lightweight AI security scanner -- detect prompt injection, PII leaks, and LLM attacks in 3 lines of Python.
@yawlabs/electron-mcp
jeffyaw
Electron.js MCP server — IPC scaffolding, security auditing, build tooling, and development intelligence for AI assistants
...morenest-langchain
rezahssini
A powerful NestJS library for building AI agents with a unified tool system, security middleware, and enterprise-grade features
...morenextjs-proxy
arcademan
Universal, secure proxy for Next.js. Centralize, audit, and control all external API calls from a single entry point.
arp-agent
zhoujiahong
Agent Reliability Platform - One package for monitoring, verification, memory, and security of AI agents. npm install arp
...moremcp-sec-scan
r00flr00fl
Opinionated remote-MCP auth & tenancy security scanner. Checks what a Streamable HTTP MCP server exposes from the outside.
...moremujin-agentaudit
Mujin Labs
Security & quality audit for AI-agent extensions (Claude Code skills, MCP servers, plugins) — scan before you install.
green_dot
topkat
A powerful TypeScript nodeJs framework for building DX friendly, secure and type-safe backend services with MongoDB integration
...moremcp-bastion-crewai
Viquar Khan
MCP-Bastion security middleware for CrewAI — prompt injection, PII, and rate-limit protection for AI agent crews
aegisq-codeshield-mcp
aegisq
AegisQ-CodeShield MCP server — AI security scanning for Claude Code, Cursor, Windsurf, Copilot, ChatGPT, Cline, and more
@devr-tools/codeguard
GitHub Actions
Repository checks across code quality, design boundaries, security, CI/CD hygiene, and AI prompt governance.
mcp-vulnscan
Static analysis tool for MCP server Python code — detects security vulnerabilities via AST and taint tracking.
breakit
kindlmann
Autonomous exploratory testing for web apps. 25 AI personas find bugs, security issues, and UX friction.
mcpsnare
Active, confirmation-driven security scanner for MCP (Model Context Protocol) servers - Burp Active Scan, for MCP.
qsag-core
AIXYBER TECH LTD (trading as Neoxyber)
Open source AI agent security toolkit — MCP poisoning scanner, ghost detection, prompt injection patterns
@mondaydotcomorg/agent-toolkit-frozen
monday.com Security
Security placeholder — claimed to prevent dependency confusion. This package name was found as an unregistered npm alias in a production codebase.
...morenpmvault
giuseppe-scotto-lavina
Agent-first local NPM registry with quarantine, prompt injection scanning, and supply chain security. Coming soon.
adapt-agent
ADAPT-Agent: Adversarial Defense & Policy Training for LLM Agents - A comprehensive library for LLM agent optimization and security
...more