Skip to main content
Glama
Remote Desktop MCP (DV)

Remote Desktop MCP (DV)

by ThinkerQAQ

RemoteDesktopMCP

简体中文

1. Introduction

RemoteDesktopMCP started with a practical goal: I wanted to use ChatGPT in the browser to work directly with files and tools on my computer—for example, reading project code, editing documentation, or running terminal commands.

ChatGPT can generate code and reason through problems, but a browser conversation alone cannot access my local files or development environment. To make it useful for these tasks, it needs tools that can perform actions on the computer.

I initially considered building those tools myself, then found that Desktop Commander already provides file operations, search, and terminal commands through MCP. There was no reason to rebuild that functionality. The remaining question was how to connect browser-based ChatGPT to tools running locally.

RemoteDesktopMCP uses OpenAI Secure MCP Tunnel for that connection. A client on the computer establishes an outbound connection to OpenAI, allowing ChatGPT to call the local Desktop Commander tools without exposing a local MCP port to the public internet or relying on Desktop Commander's hosted remote service.

The project also provides installers, configuration, and service management for Windows, Linux, and macOS. Once installed, you configure a Tunnel, start the service, and register the plugin in ChatGPT to work with local files and terminal commands from the browser.

Related MCP server: CodePier

2. Quick Start

Install RemoteDesktopMCP, configure the connection, and verify it in ChatGPT. You need an internet connection and a ChatGPT account or workspace that supports custom MCP Tunnel connections. Installers are available for Windows x64, Linux x64, and Intel macOS.

2.1. Install

Download the installer for your system from the latest Release.

2.1.1. Graphical Interface

Windows

Run RemoteDesktopMCP-v*-windows-amd64.exe and complete the installation wizard. Open Configure Tunnel from the Start Menu.

macOS

Open RemoteDesktopMCP-v*-darwin-amd64.dmg and run the installer application. On the completion screen, select Open RemoteDesktopMCP configuration to open the configuration UI in your browser.

Linux

Run RemoteDesktopMCP-v*-linux-amd64.run from your desktop environment. If execution is blocked, enable it in the file properties. On the completion screen, select Open RemoteDesktopMCP configuration to open the configuration UI in your browser.

2.1.2. Command Line

Windows

Open a terminal in the download directory:

for %F in (RemoteDesktopMCP-v*-windows-amd64.exe) do "%~fF" --accept-licenses --default-answer --confirm-command install
macOS

Mount the DMG and run its installer:

dmg=$(find . -maxdepth 1 -name 'RemoteDesktopMCP-v*-darwin-amd64.dmg' -print -quit)
mount=$(mktemp -d)
hdiutil attach -nobrowse -readonly -mountpoint "$mount" "$dmg"
app=$(find "$mount" -maxdepth 1 -name '*.app' -print -quit)
installer=$(find "$app/Contents/MacOS" -maxdepth 1 -type f -perm -111 -print -quit)
QT_QPA_PLATFORM=offscreen "$installer" --root "$HOME/RemoteDesktopMCP" --accept-licenses --default-answer --confirm-command install
hdiutil detach "$mount"
Linux
chmod +x ./RemoteDesktopMCP-v*-linux-amd64.run
QT_QPA_PLATFORM=offscreen ./RemoteDesktopMCP-v*-linux-amd64.run --root "$HOME/RemoteDesktopMCP" --accept-licenses --default-answer --confirm-command install

After installation, configure the connection in the next section.

2.2. Configuration

Create a Tunnel ID and a Runtime API Key.

2.2.1. Graphical Interface

Enter both values in the configuration UI, save the configuration, start the service, and refresh status to confirm Local Tunnel: Connected.

2.2.2. Command Line

From the installation directory:

./bin/remotedesktopmcp configure
./bin/remotedesktopmcp start
./bin/remotedesktopmcp status

On Windows, use .\bin\remotedesktopmcp.exe with the same subcommands. Interactive configure hides the Runtime API Key. For automation, use configure --id <tunnel-id> --api-key-stdin and pass the key through standard input. Use stop to stop the service.

2.3. Verify in ChatGPT

Open ChatGPT Plugins, register a custom MCP Tunnel using the same Tunnel ID, and authorize the connection. Refer to the OpenAI connection guide for current account-specific steps.

In ChatGPT, select the plugin and call the read-only list_sessions tool. An empty list is a valid result.

2.4. Troubleshooting

If the Tunnel is not connected, verify the saved ID, key, network, and local service status. If ChatGPT cannot call the tools despite a connected Tunnel, verify that its plugin is registered and selected. Do not share credentials or local logs containing private data.

3. Development

You can skip this section if you're using an installer. To work with the source, install Git, npm, and a Node.js version supported by package.json:

git clone https://github.com/ThinkerQAQ/remote-desktop-mcp.git
cd remote-desktop-mcp
npm ci --no-audit --no-fund
npm run check
npm run smoke
npm run audit:high

check runs unit and compatibility tests; smoke initializes the MCP server and makes a read-only call. On Windows CMD, run npm.cmd directly.

Changes go through pull-request review and Squash Merge. See Installer CI and Release CI for the package builds.

4. License

Original project code is licensed under Apache-2.0. Third-party licenses are listed in THIRD_PARTY_NOTICES.md.

RemoteDesktopMCP reads, writes, and runs commands using the permissions of the operating-system account that starts it; it does not add a tool-level sandbox. Use an appropriately restricted account and review plugin permissions. MCP requests and results may be sent to the connected AI service. Keep config.toml, runtime/, keys, and logs private.

Please report security issues privately through GitHub Security Advisories.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Connects ChatGPT and MCP clients to authorized local development environments, enabling secure file access, shell execution, persistent tasks, browser/desktop control, and remote management of projects.
      21
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Connects ChatGPT Web to a local development environment, enabling file reads and patches, shell execution, plan updates, and isolated worktree coordination through permissioned MCP tools.
      15
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables ChatGPT to operate a local workstation through a secure outbound tunnel, exposing 44 MCP tools for files, git, projects, processes, browsers, native apps, Office documents, and optional Codex delegation across macOS, Linux, and Windows.
      1
      MIT