MCP低风险未认领

agent-firewall-mcp

Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.

mlawsonkingmlawsonking/agent-firewall-mcp★ 1更新于 2026年8月10日

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.mlawsonking/agent-firewall-mcp",
  "description": "Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.",
  "repository": {
    "url": "https://github.com/mlawsonking/MCP",
    "source": "github",
    "subfolder": "agent-firewall-mcp"
  },
  "version": "1.3.0",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "agent-firewall-mcp",
      "version": "1.3.0",
      "transport": {
        "type": "stdio"
      }
    }
  ]
}

权限

声明检测
运行代码—node
安装—npm:agent-firewall-mcp@1.3.0
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

  1. #11.3.0最新2026年10月7日