AgentHubAgentHub

agent-immune

MCP ServerMCP Registry官方收录

io.github.denial-web/agent-immune · v0.2.2

AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening

概览

agent-immune 是一个MCP Server,收录自 官方 MCP Registry。支持 stdio 传输。本页提供 Cursor、Claude Code 等客户端的安装配置片段。

安装

选择你的平台查看安装方式

{
  "mcpServers": {
    "agent-immune": {
      "command": "uvx",
      "args": [
        "agent-immune"
      ]
    }
  }
}

相关资源

统一 Manifest

{
  "id": "io.github.denial-web/agent-immune",
  "type": "mcp-server",
  "version": "0.2.2",
  "displayName": "agent-immune",
  "description": "AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening",
  "repository": {
    "url": "https://github.com/denial-web/agent-immune",
    "source": "github"
  },
  "distribution": {
    "packages": [
      {
        "registryType": "pypi",
        "identifier": "agent-immune",
        "version": "0.2.2",
        "transport": "stdio"
      }
    ],
    "remotes": []
  },
  "dependencies": [],
  "installTargets": [
    "claude-code",
    "claude-desktop",
    "cursor",
    "vscode"
  ],
  "keywords": [],
  "provenance": {
    "origin": "official-mcp-registry",
    "originalId": "io.github.denial-web/agent-immune",
    "originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.denial-web%2Fagent-immune/versions/latest",
    "isOfficial": true,
    "status": "active"
  }
}
agent-immune — MCP Server 安装与配置 · AgentHub