AI Skill Hub 推荐使用:MCP安全网关 是一款优质的MCP工具。AI 综合评分 7.8 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
MCP安全网关 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
MCP安全网关 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/provnai/McpVanguard
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"mcp----": {
"command": "npx",
"args": ["-y", "mcpvanguard"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 MCP安全网关 执行以下任务... Claude: [自动调用 MCP安全网关 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"mcp____": {
"command": "npx",
"args": ["-y", "mcpvanguard"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Security gateway for MCP agents and tool servers.
McpVanguard sits between an AI agent and an MCP server, normalizes and inspects tool traffic in real time, and enforces a layered policy before sensitive calls reach the underlying tool. It runs locally in front of stdio servers or as a hosted gateway over SSE and Streamable HTTP.
Product profiles — monitor, balanced, strict — let you adopt incrementally: start with audit-only discovery, move to balanced enforcement, then enable strict hardening for production-sensitive systems.
Existing MCP servers do not need to be rewritten.
initialize and tools/listserver_id traceabilityreceipt_v1 JSONL emission for offline-verifiable runtime evidence with mcp-receipt after export/signingBootstrap a local workspace:
```bash
McpVanguard is best understood as a security gateway for MCP workflows.
Typical path:
AI Agent -> McpVanguard -> MCP Server -> Tools / Files / External Systems
Install the package:
pip install mcp-vanguard
Wrap a local stdio MCP server:
```bash
vanguard init
vanguard configure-claude
The optional Layer 2 semantic scorer supports multiple backends. The first configured backend wins.
| Backend | Env Vars | Notes |
|---|---|---|
| **Universal Custom** | VANGUARD_SEMANTIC_CUSTOM_KEY, related custom vars | Fast inference providers such as Groq or DeepSeek |
| **OpenAI** | VANGUARD_OPENAI_API_KEY | Default model: gpt-4o-mini |
| **Ollama** | VANGUARD_OLLAMA_URL | Local execution, no API key required |
For a more detailed local/offline setup guide, see docs/LOCAL_SEMANTIC_MODE.md.
Does this replace my MCP server? No. McpVanguard sits in front of your existing MCP server and enforces policy before calls reach it.
Do I need to rewrite tools or agent code? Usually no. Most setups start by routing one workflow through McpVanguard.
Is this only for hosted setups? No. It supports local-first stdio wrapping and hosted gateway modes.
创新的MCP安全方案,填补AI代理工具调用的安全空白。架构清晰,代码质量良好,但社区成熟度有限,适合安全敏感的企业先行试用。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,MCP安全网关 是一款质量良好的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | McpVanguard |
| 原始描述 | 开源MCP工具:Open-source MCP security gateway that sits between AI agents and tools to inspec。⭐13 · Python |
| Topics | MCP协议AI安全代理网关工具检查开源 |
| GitHub | https://github.com/provnai/McpVanguard |
| License | MIT |
| 语言 | Python |
收录时间:2026-06-09 · 更新时间:2026-06-09 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端