canack/bad-mcp

10 intentionally malicious MCP servers that exploit protocol features to attack AI clients. For security research and defense testing.

语言：Go · GitHub 星标：9 · Fork：1

话题：ai-security · llm-security · mcp · mcp-server · model-context-protocol · red-team · rug-pull · security

在 GitHub 上查看原仓库