Best Safety AI Skills & MCP Servers

MCP server that connects Redash to Claude AI — query data, manage dashboards, and run SQL with natural language, with built-in SQL safety guards.

xCLAUDE — A receipt for your AI. Local audit log for every Claude tool call.

Pre-execution governance for AI agents. Intercepts MCP tool calls before execution with deterministic blocking, human-in-the-loop holds, and behavioral drift detection.

MCP server exposing macOS Terminal.app to AI agents via AppleScript / JXA. List windows, read scrollback, execute commands, clear buffers — with three-tier safety patterns and confirmation dialogs.

MCP server for safe AI-agent database access through backstop.

Public Preview — AgentOS MCP Server for Claude Desktop: Build, deploy, and manage policy-compliant autonomous agents

Pre-execution governance for AI agents. Intercepts MCP tool calls before execution with deterministic blocking, human-in-the-loop holds, and behavioral drift detection.

Drop-in optimization toolkit for Claude Code — 15 agents, token savings, safety hooks, UI pipeline

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 safety — so AI agents perceive and act on your data deter

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 safety — so AI agents perceive and act on your data det

A tiny TypeScript approval gate for AI tool calls, MCP tools, and human-in-the-loop workflows.

건설현장의 법정 안전문서 작성을 더 빠르고 정확하게. 산안법·기준규칙·중처법·KOSHA Guide를 기반으로 안전관리자와 현장소장의 문서 작성과 검토를 돕는 오픈소스 도구입니다.

Vehicle safety data from NHTSA — recalls, complaints, crash ratings, investigations, VIN decoding.

Enforce consistent C++ style and best practices across your codebase. Analyze naming, memory safety, and const correctness, and get actionable modernization suggestions up to C++23. Accelerate reviews with ready-made prompts and quick access to curated guidelines.

Token safety for AI agents. 27 scam patterns, real honeypot simulation via DEX swap testing, 6 EVM chains. 38 MCP tools including DeFi data, agent economy with AIGEN rewards, task board with bounties.

Index and search codebases using structured schemas for deep code analysis. Audit specific domains or security-related functions to ensure code quality and safety. Explore complex codebases with high-level overviews to understand structure and patterns quickly.

Search live food safety data from FDA, FSIS, CDC, and city health departments (NYC, Chicago, SF, Seattle, Boston). 5 tools: search recalls, outbreaks, alerts, restaurant inspection articles, and food safety guides. Data aggregated from 25+ public government sources via Panko Aler

Access and search comprehensive Canadian building regulations for construction and compliance reference. Navigate complex code hierarchies to find specific requirements for fire safety, structural integrity, and accessibility. Simplify project planning by quickly retrieving detai

Access real-time weather forecasts and climate data across Indonesia. Stay informed about recent seismic activity and natural disasters with official government alerts. Plan activities and ensure safety by monitoring environmental conditions from the national meteorological agenc

Evaluate crypto token safety with real-time trust scores and structural risk signals. Identify potential market distress and impending collapses to safeguard your digital investments. Compare assets head-to-head using multi-dimensional security and compliance metrics.