10 packages found
Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enfor
AI-first security scanner with 79 analyzers, 40,000+ detection rules, and repo poisoning detection for AI/ML, LLM agents
Inkog MCP Server — the pre-flight check for AI agents
This repository contains Cursor Security Rules designed to improve the security of both development workflows and AI age
AI Agent Security Middleware — 8-layer defense, DLP data flow, prompt injection detection, zero dependencies. SDK + MCP
Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability
The approval and accountability layer for agentic AI. Identity → Policy → Approval → Trace. Try: npx sidclaw-mcp-guard d
Open-source runtime security and governance for AI agents, MCP tools, robotics, industrial automation, and physical AI.
[DEPRECATED] Moved to microsoft/agent-governance-toolkit
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more fra