对大模型的输入与输出做内容安全检测，实时识别合规、伦理与安全风险并拦截，策略可定制。
Setup
This project documents no single launch command; follow its repository instructions.
创思大模型安全 MCP
创思OfficialChina
Related
More- AAIM Guard MCPAIM IntelligenceGives agents safety guidelines and content analysis to guard MCP tool use and AI chats against unsafe input.Security23 Repository stars
- AAperion ShieldAperionLocal proxy that wraps MCP servers and blocks destructive calls such as dropping tables or recursive deletes, pins tool catalogs and scans for tool poisoning.Security11 Repository stars
- SMCP SeatbeltKryptosAIWraps MCP servers in a default-deny policy proxy that blocks dangerous tool calls at runtime.Security3 Repository stars
- SSafeLine MCPChaitin TechOfficialChinaRead-only access to SafeLine WAF instances, letting agents query attack events through the SafeLine API.Security22.9k Repository stars
- SSemgrep MCPSemgrepOfficialScans code for security vulnerabilities using Semgrep.Security17.2k Repository stars
- BBurp Suite MCP ServerPortSwiggerOfficialBurp Suite extension that lets AI clients connect to Burp for web security testing tasks.Security1.2k Repository stars