MCP低风险未认领
mcp-seatbelt
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
KryptosAIkryptosai/mcp-seatbelt
server.json
{
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"name": "io.github.KryptosAI/mcp-seatbelt",
"description": "MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.",
"repository": {
"url": "https://github.com/KryptosAI/mcp-seatbelt",
"source": "github"
},
"version": "0.7.0",
"packages": [
{
"registryType": "npm",
"identifier": "@kryptosai/mcp-seatbelt",
"version": "0.7.0",
"transport": {
"type": "stdio"
}
}
]
}权限
声明检测
运行代码—
node安装—
npm:@kryptosai/mcp-seatbelt@0.7.0安装时运行脚本—无
网络无无
需要的凭据无无
工作区外的路径—无
智能体工具—无
检查
低风险 · 没有发现需要提醒的地方。
未经人工审核 · 已做规则检查;模型审核尚未开启。
版本
- #10.7.0最新2026年10月7日
mcp-seatbelt在 Codeg 中打开