Skip to main content
Glama

💻 mcp-vnc

Node.js Version License: MIT npm version

一个 Model Context Protocol (MCP) 服务器,使 AI 代理能够远程控制 Windows、Linux、macOS 或任何其他可以运行 VNC 服务器的东西(别担心,应该没问题)。

Screenshot

🚀 快速开始

从 NPM 安装

npm install -g @hrrrsn/mcp-vnc

从源码安装

git clone https://github.com/hrrrsn/mcp-vnc
cd mcp-vnc
npm install
npm run build

Related MCP server: mcp-vnc

⚙️ 配置

Claude Desktop

  1. 找到并打开你的 Claude Desktop 配置文件:

    • macOS~/Library/Application Support/Claude/claude_desktop_config.json

    • Windows%APPDATA%\Claude\claude_desktop_config.json

    • Linux~/.config/Claude/claude_desktop_config.json

  2. 添加以下配置:

使用 NPM 安装:

{
  "mcpServers": {
    "vnc-controller": {
      "type": "stdio",
      "command": "mcp-vnc",
      "env": {
        "VNC_HOST": "192.168.1.100",
        "VNC_PORT": "5900",
        "VNC_PASSWORD": "your-vnc-password",
        "VNC_TIMEOUT": "30000"
      }
    }
  }
}

从源码构建:

{
  "mcpServers": {
    "vnc-controller": {
      "type": "stdio",
      "command": "node",
      "args": ["dist/index.js"],
      "cwd": "/path/to/mcp-vnc",
      "env": {
        "VNC_HOST": "192.168.1.100",
        "VNC_PORT": "5900",
        "VNC_PASSWORD": "your-vnc-password",
        "VNC_TIMEOUT": "30000"
      }
    }
  }
}

VNC_TIMEOUT(可选)设置每次工具调用等待 VNC 服务器连接并交付初始帧的时间,单位为毫秒。默认为 30000

VS Code

请参阅 VS Code 文档

HTTP 传输(Streamable HTTP)

默认情况下,服务器使用 stdio。要改为通过 HTTP 暴露它:

# Via environment variables
VNC_HOST=192.168.1.100 VNC_PORT=5900 VNC_PASSWORD=secret \
MCP_TRANSPORT=http MCP_PORT=3000 mcp-vnc

# Or via CLI arguments
mcp-vnc --http --port 3000

MCP 端点随后可在 http://localhost:3000/mcp 访问。客户端配置示例:

{
  "mcpServers": {
    "vnc-controller": {
      "type": "http",
      "url": "http://localhost:3000/mcp"
    }
  }
}

设置

默认值

描述

MCP_TRANSPORT

stdio

设置为 http 以启用 HTTP 传输

MCP_PORT

3000

HTTP 监听端口

🛠️ 可用工具

MCP 服务器提供以下用于远程桌面控制的工具:

🖱️ 鼠标控制

参数

必填

类型

描述

默认值

x

number

X 坐标

-

y

number

Y 坐标

-

button

string

鼠标按钮(leftrightmiddle

left

double

boolean

双击而非单击

false

示例: vnc_click(x=100, y=200, button="right", double=true)

参数

必填

类型

描述

x

number

X 坐标

y

number

Y 坐标

示例: vnc_move_mouse(x=500, y=300)

⌨️ 键盘控制

参数

必填

类型

描述

key

string

要按下的按键或组合键

支持的按键:

  • 单个按键aEnterF1EscapeUpDownTabSpace

  • 组合键Ctrl+cAlt+F4Ctrl+Alt+DeleteShift+Tab

  • 修饰键CtrlAltShiftSuper/WinMeta/Cmd

示例:

  • vnc_key_press(key="Enter")

  • vnc_key_press(key="Ctrl+Alt+Delete")

📝 文本输入

参数

必填

类型

描述

默认值

text

string

要输入的文本

-

enter

boolean

输入后按 Enter

false

示例: vnc_type_text(text="Hello World!", enter=true)

参数

必填

类型

描述

lines

string[]

要输入的行数组

示例: vnc_type_multiline(lines=["Line 1", "Line 2", "Line 3"])

📸 屏幕捕获

参数

必填

类型

描述

默认值

delay

number

截图前延迟(0-300000ms)

0

示例: vnc_screenshot(delay=1000) - 等待 1 秒后再截图

🤝 贡献

欢迎贡献!请随时提交拉取请求。

📄 许可证

本项目采用 MIT 许可证授权 - 详见 LICENSE 文件。

A
license - permissive license
A
quality
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    An MCP server that allows AI agents to remotely control Windows, Linux, and macOS systems via VNC. It provides tools for mouse and keyboard interaction, text input, and screen capturing.
    6
    527
    55
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables MCP-compatible LLMs to interact with any desktop accessible over VNC, providing tools for screen reading (OCR), mouse and keyboard control, and automation.
    13
    AGPL 3.0
  • A
    license
    B
    quality
    D
    maintenance
    Empowers AI agents to see, reason, and control computers via VNC, providing advanced vision features like OCR and image search, human-like input control, and optional SSH remote command execution.
    21
    1
    MIT

View all related MCP servers

Related MCP Connectors

  • Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.

  • Eyes and hands on real Windows PCs — observe, click, type via Glasswarp API.

  • OCR, transcription, file extraction, and image generation for AI agents via MCP.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/robotic-wings/vnc-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server