cloud-to-local
Enables cloud agents to securely operate local machine resources (files, commands, screenshots) via standard MCP protocol.
README
Cloud2Local
让云端智能体安全地操作你的本机。
云端 Agent 本来够不着你的电脑。Cloud2Local 在本机开一个 MCP Server,把文件读写、目录浏览、白名单命令、截屏等能力暴露成标准 MCP 接口;云端填 URL + Token 即可接入。
项目特色
| 特色 | 说明 |
|---|---|
| 标准 MCP 协议 | 支持 Streamable HTTP(/mcp)与兼容旧客户端的 SSE(/sse) |
| 云端即连 | 启动后直接给出云端接入地址,可一键复制客户端配置 |
| 按需公网暴露 | 默认仅本机访问,需要时再手动开启自动暴露 |
| 鉴权与边界 | Token 鉴权、fileRoot 路径沙箱、命令白名单、脚本超时 |
| 本机工具箱 | read_file / write_file / list_directory / run_command / screenshot |
| 桌面可视化 | 状态、配置、运行日志、启停都在 GUI 里完成 |
| 跨平台 | Windows / macOS / Linux(Electron) |
本机已经在跑的 Agent 不必再绕一层 MCP 调本机;这套主要给 云端 / 远程智能体 用。
连上后工具列表由协议list_tools自动发现,不需要客户端手写工具目录。
30 秒上手
两个端口别混: 本机 MCP 默认 8000;云端访问默认公网口 18000。云端不要填 8000。
- 启动应用,首页先连上外网通道
- 打开 MCP Server 页
- 设置 Token、收窄 文件根目录、确认允许命令
- 本机端口
8000,公网端口18000,先设 Token;需要公网时再开「自动公网暴露」 → 保存 → 启动 - 确认「运行中」,云端地址端口是 18000
- 云端客户端填:
{
"mcpServers": {
"cloud-to-local": {
"url": "http://PUBLIC_HOST:18000/mcp",
"headers": {
"Authorization": "Bearer YOUR_TOKEN"
}
}
}
}
服务器至少放行:控制口 7000 + 公网业务口 18000。
更细的接入步骤见 docs/云端MCP接入教程.md。
Skill:docs/cloud-to-local/(可装到 WorkBuddy 等客户端)。
安全(必读)
这是把本机能力放到网上,请当生产接口对待:
- Token 必开,不要空着给公网
- fileRoot 收窄到工作目录,不要整盘
- allowedCommands 只留必要命令
- 不用时 停止 Server(若开了自动暴露会一并关掉)
- 有条件上 HTTPS / 反代;裸 HTTP 会明文传 Token
开发
npm install
# Windows / 部分环境需清除 ELECTRON_RUN_AS_NODE
env -u ELECTRON_RUN_AS_NODE npm run dev
npm run build
npm run build:electron
技术栈:Electron + Vue3 + Vite + Element Plus + MCP SDK。
License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.