Sanctuary Framework
未认领Open-source security for AI agents: kernel-enforced egress control on macOS and Linux, keys only the operator holds, tamper-evident audit. One command protects Claude Code, Cursor, or any MCP harness. No vendor in the path.
agent-infrastructureai-agentsdecentralized-identityopen-standardprivacyai-agent-securityclaude-codeegress-controlendpoint-securitymcp
安装
$
npx @sanctuary-framework/mcp-server protect --claude-code