Skip to main content
Glama
README.md
# lighthouse-mcp 🦞

MCP Server for Tencent Cloud Lighthouse(轻量应用服务器)管理。

让 AI Agent(Claude Code / OpenClaw / Cursor)通过自然语言管理你的 Lighthouse 服务器。

## 已支持的工具

| 工具 | 说明 |
|------|------|
| `describe_regions` | 查询所有可用地域 |
| `describe_instances` | 查询实例列表 |
| `get_monitor_data` | 获取监控数据(CPU/内存/带宽/磁盘IO) |
| `describe_firewall_rules` | 查看防火墙规则 |
| `create_firewall_rules` | 添加防火墙规则 |
| `delete_firewall_rules` | 删除防火墙规则 |
| `describe_snapshots` | 查看快照列表 |
| `execute_command` | 远程执行命令(TAT) |
| `describe_command_tasks` | 查询命令执行状态 |

## 安装

```bash
npm install -g lighthouse-mcp
# 或
npx lighthouse-mcp
```

## 配置

设置腾讯云 API 密钥:

```bash
export TENCENT_SECRET_ID="your_secret_id"
export TENCENT_SECRET_KEY="your_secret_key"
```

或创建 `.env` 文件:

```env
TENCENT_SECRET_ID=your_secret_id
TENCENT_SECRET_KEY=your_secret_key
```

密钥获取:[腾讯云控制台 > API密钥管理](https://console.cloud.tencent.com/cam/capi)

## 在 MCP 客户端中使用

### Claude Code

添加到 `~/.claude/claude_desktop_config.json` 或项目 `.mcp.json`:

```json
{
  "mcpServers": {
    "lighthouse": {
      "command": "npx",
      "args": ["-y", "lighthouse-mcp"],
      "env": {
        "TENCENT_SECRET_ID": "your_secret_id",
        "TENCENT_SECRET_KEY": "your_secret_key"
      }
    }
  }
}
```

### OpenClaw

添加到 `openclaw.json` 的 `tools.mcp` 配置:

```json
{
  "tools": {
    "mcp": {
      "lighthouse": {
        "command": "node",
        "args": ["dist/index.js"],
        "cwd": "/path/to/lighthouse-mcp",
        "env": {
          "TENCENT_SECRET_ID": "...",
          "TENCENT_SECRET_KEY": "..."
        }
      }
    }
  }
}
```

## 示例对话

```
你: 我有几台服务器?状态怎么样?
Agent: [调用 describe_instances] → 你有 2 台服务器,上海那台运行中...

你: 帮我把上海的服务器防火墙打开 443 端口
Agent: [调用 create_firewall_rules] → 已添加 TCP 443 规则

你: 最近的 CPU 使用率怎么样?
Agent: [调用 get_monitor_data] → 最近 6 小时 CPU 均值 12%...
```

## 技术栈

- `@modelcontextprotocol/sdk` — MCP 协议 SDK
- `tencentcloud-sdk-nodejs-lighthouse` — 腾讯云 Lighthouse SDK
- TypeScript + ES Modules

## License

MIT

TDQS

B3.4/5.0

Scored across 9 tools

Disambiguation5/5

Each tool targets a distinct operation: firewall management (create/delete/describe), command execution and task status, instance listing, region listing, snapshots, and monitoring. No two tools overlap in purpose.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern in snake_case (e.g., create_firewall_rules, describe_instances, get_monitor_data). Verbs like describe, create, delete, execute, get are used predictably.

Tool Count5/5

With 9 tools, the server is well-scoped for managing key aspects of Lighthouse instances: firewall, command execution, monitoring, and listing resources. The number is appropriate without being overwhelming.

Completeness3/5

The tool set covers firewall, command execution, monitoring, and listing of instances/snapshots/regions, but lacks instance lifecycle operations (create, delete, stop, start) and snapshot CRUD (only describe). This leaves notable gaps for full instance management.

Maintenance

ActivityInactive
ResponsivenessNo issues