什么是 #safety MCP 服务器?
标记为 #safety 的 MCP 服务器实现了 Model Context Protocol,让 Claude、Cursor、VS Code 等 AI 助手可以访问 safety 相关的工具、数据或 API。
以下 MCP 服务器和客户端均标记为 #safety——安装后即可让 Claude、Cursor、VS Code 等支持 MCP 的客户端获得 safety 相关能力。
voix-sys
Cosmetic Ingredient Risk Engine — deterministic INCI safety scoring API for AI agents
depurecoindustrialvacuums-boop
Remote MCP Server (WebMCP) for industrial vacuum cleaner exploration and configuration. Helps to choose the right vacuuming solution for each specific dust extraction application.
Br0ski777
Token contract safety scanner (honeypot, tax, proxy, blacklist, risk score) -- x402 micropayment API + MCP server for AI agents
charlieSAX
Real-time entity verification API for AI agents. Verify emails, URLs, and domains before your agent acts on them. Returns trust scores (0-1), verdicts (pass/warn/fail), and detailed signals. Free tier (50 calls/day) + instant metered access for agents with wallets ($0.003/call).
contextkits
Check workplace safety compliance against OSHA General Industry standards (29 CFR 1910) with cited regulation sections and corrective actions.
Copliancy Inc
Incident reporting and claims management for multi-location businesses: incidents, claims, tasks, risk checks and inspections, with role and location limits on every call.
writesdavid
17 US federal data domains as MCP tools. FDA drugs, EPA water, CMS hospitals, NHTSA cars, BLS jobs, Census demographics, SEC filings, NOAA weather, and more. Signed responses with provenance
EthanKlocked
Safe-by-default local stdio MCP server for the official Toss Securities Open API. Read-only market/account tools are available by default; order operations require explicit trading gates, dry-run defaults, confirmation, and max-order safeguards.
RedCiprianPater
NWO.CAPITAL is a multi-domain MCP server exposing 201 tools across 30 categories behind one Render-hosted endpoint with on-chain identity on Base Mainnet. Tools span autonomous-agent infrastructure, humanoid robotics + ROS2 control, biometric identity (ECG-based, soul-bound NFTs)
brack-6
Runtime security oracle for AI agents — scan prompts, tool calls, and outputs before execution. Pay-per-call via x402/USDC, no accounts needed.
关于 #safety 标签下 MCP 服务器和客户端的常见问题
标记为 #safety 的 MCP 服务器实现了 Model Context Protocol,让 Claude、Cursor、VS Code 等 AI 助手可以访问 safety 相关的工具、数据或 API。
mcp.so 目前收录了 10 个标记为 #safety 的 MCP 服务器和客户端。
打开下方任意服务器页面,将安装配置复制到 Claude Desktop、Cursor、VS Code 或其他 MCP 客户端的配置中即可——远程服务器无需单独下载。