20 packages found
Open-source runtime security and governance for AI agents, MCP tools, robotics, industrial automation, and physical AI.
MCP server for Vorim AI — AI agent identity, permissions, and audit trails. 17 tools for Claude, Cursor, VS Code, and an
Inkog MCP Server — the pre-flight check for AI agents
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more fra
Rust MCP server with 168 security tools for Claude — DNS/DNSSEC, TLS, email security, OSINT, threat intelligence, supply
GUARDRAIL - MCP Security - Gateway for Unified Access, Resource Delegation, and Risk-Attenuating Information Limits
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.
Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enfor
MISP (core software) - Open Source Threat Intelligence and Sharing Platform
[DEPRECATED] Moved to microsoft/agent-governance-toolkit
Offensive-security MCP server with 205 wrapped tools, 17 specialist agents, and 60 SPA-aware probes for OWASP Top 10. CL
Mac-resident MCP server: securely proxies Mail / Calendar / Drive / Contacts to AI agents over stdio or Tailnet HTTP, wi
🦞 MCP server for OpenClaw - secure bridge between Claude.ai and your self-hosted OpenClaw assistant with OAuth2 authent
AI-first security scanner with 79 analyzers, 40,000+ detection rules, and repo poisoning detection for AI/ML, LLM agents
MCP server for Kali Linux penetration testing - 130 tools for AI-assisted security testing - Giving Agents access to ful
Automated security investigation tool using Microsoft MCP Servers, GitHub Copilot, Python Modules and custom copilot-ins
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 238 commands, 224 MC
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability
MCP server — read-only log access for AI assistants. Debug your Linux server with AI, without giving the AI shell access