Results for “safety”

[DEPRECATED] Moved to microsoft/agent-governance-toolkit

Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability

The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.

rUvOS — the agentic operating system. A single static Rust binary that runs as an MCP server, giving Claude Code persist

A generic mcp server fuzzer

Open-source permission control plane for AI agents. Scan, enforce, and audit every tool call.

Secure MCP server for safe AI-powered terminal access with risk analysis, sandboxing, logging, filesystem protection, an

A Model Context Protocol (MCP) server that provides comprehensive SQLite database operations for LLMs. This server enabl

Local-first production-readiness system for AI-built apps: read-only audit, evidence-based 0-100 score, guided fixes, le

Pre-install trust layer for MCP servers, AI skills & npm packages — the @mcpskillsio/server MCP server (io.mcpskills/ser

Production-grade Playwright + TypeScript QA framework with AI-powered testing, LLM-as-Judge evaluation, MCP server, 7 CL

🛡️The governance runtime for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit

Agentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.

A Postgres MCP server for agents — layered safety (role grant + pglast AST guard + per-tx envelope + audit log), schema

Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.

Security infrastructure your AI can't be — deterministic, daily CVE intel past your model's training cutoff, whole-repo-

🔥🔒 Awesome MCP (Model Context Protocol) Security 🖥️

AI Agent Security Middleware — 8-layer defense, DLP data flow, prompt injection detection, zero dependencies. SDK + MCP

MCP server combining Qdrant vector search, Neo4j knowledge graphs, and Crawl4AI web intelligence with agentic RAG capabi

Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enfor

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

A curated, DevOps-focused list of Model Context Protocol (MCP) servers—covering source control, IaC, Kubernetes, CI/CD,

A Security-centric MCP Server providing enterprise-grade filesystem powers to AI assistants—read, write, edit, and manag

Static pre-install security scanner for MCP (Model Context Protocol) servers — `npx mcpaudit <path>` flags command injec

Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for Model Con

MCP server for structured email access via a local shadow database. Exposes a minimal, auditable API surface — AI agents

Secure MCP server for safe, read-only DB access by AI agents, with SQL guardrails, table allowlists, PII masking, and au

Provision, secure, backup, and manage self-hosted servers — full lifecycle, one CLI.

LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more fra

DepScope — Package Intelligence for AI Agents. 22 MCP tools, 19 ecosystems, free, no auth. https://depscope.dev

Mac-resident MCP server: securely proxies Mail / Calendar / Drive / Contacts to AI agents over stdio or Tailnet HTTP, wi

A production-grade, schema-aware PostgreSQL MCP server for enterprise AI. Features Zero-Trust SQL validation, multi-tier

Enterprise AI bastion host for secure AI API and MCP access, with unified proxying, RBAC, audit logs, rate limiting, and

Supply chain risk scorer for npm and PyPI — single-maintainer CRITICAL flags before attacks happen

MCP server that enables AI agents to perform comprehensive web audits using Google Lighthouse with 13+ tools for perform

A read-only Kubernetes MCP server: list resources, get resource details, retrieve pod logs, discover API resources, and

9 MCP servers for React + TypeScript automation — component scaffolding, dep auditing, WCAG checking, test generation, T

NOT for educational purposes: An MCP server for professional penetration testers including STDIO/HTTP/SSE support, nmap,

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Olla

🤖 AI code quality gate for AI-generated code. Detects hallucinated packages, phantom dependencies, stale APIs, and more

Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, SHA-256 tamper detection, 17 MC

MCP server for Screaming Frog SEO Spider — headless crawls, data export, and a technical SEO scan skill for Claude. Patc

AI-first security scanner with 79 analyzers, 40,000+ detection rules, and repo poisoning detection for AI/ML, LLM agents

This repository contains Cursor Security Rules designed to improve the security of both development workflows and AI age

Open-source toolkit for the QVeris capability routing network: CLI, MCP server, Python SDK, skills, and REST API docs fo

A Model Context Protocol (MCP) server for webhook.site - instantly capture HTTP requests, emails, and DNS lookups. Perfe