MCP低风险未认领

gsep-mcp

AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.

gsepcoregsepcore/gsep-mcp更新于 2026年5月5日

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.gsepcore/gsep-mcp",
  "description": "AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.",
  "repository": {
    "url": "https://github.com/gsepcore/gsep-mcp",
    "source": "github"
  },
  "version": "1.0.0",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "@gsep/mcp",
      "version": "1.0.2",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "Anthropic API key (use this OR OPENAI_API_KEY OR OLLAMA_HOST)",
          "format": "string",
          "isSecret": true,
          "name": "ANTHROPIC_API_KEY"
        },
        {
          "description": "OpenAI API key (use this OR ANTHROPIC_API_KEY OR OLLAMA_HOST)",
          "format": "string",
          "isSecret": true,
          "name": "OPENAI_API_KEY"
        },
        {
          "description": "Ollama server URL for local models (e.g. http://localhost:11434)",
          "format": "string",
          "name": "OLLAMA_HOST"
        },
        {
          "description": "Intelligence preset: minimal, standard, conscious, or full (default: full)",
          "format": "string",
          "name": "GSEP_PRESET"
        }
      ]
    }
  ]
}

权限

声明检测
运行代码—node
安装—npm:@gsep/mcp@1.0.2
安装时运行脚本—无
网络无无
需要的凭据ANTHROPIC_API_KEYOPENAI_API_KEYANTHROPIC_API_KEYOPENAI_API_KEY
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. #11.0.0最新2026年10月7日