ShortlistFirst-party MCP

Remote Desktop Commander

by github:desktop-commander

Updated October 21, 2026

Developer ToolsSoftware & Technology

MCP100 verdict

Not currently recommended. Hosted Desktop Commander MCP service that relays an OAuth-authenticated AI client to a paired real computer with filesystem and terminal access. Capabilities: Read and modify local files through the paired computer; Run terminal/shell commands; Perform development and automation tasks on the real machine

MCP100 Assessment

Editorial verdict

Hosted Desktop Commander MCP service that relays an OAuth-authenticated AI client to a paired real computer with filesystem and terminal access. Capabilities: Read and modify local files through the paired computer; Run terminal/shell commands; Perform development and automation tasks on the real machine

Reviewed October 21, 2026

Task Fit

Mapped

Developer workflows

Trust

Status warning

maintenance_source_health; client_coverage; tool_contract; install_supply_chain; advisory_freshness; adoption_evidence_presence

Maintenance

Date unavailable

No dated repository or package update is currently stored.

Popularity

Signals unavailable

No independently comparable adoption metric is currently stored.

Best for

Users who specifically need remote MCP access to their own machine and can isolate a dedicated machine/account/workspace.

Not ideal for

Users who need a broadly proven, low-risk, fully mature Recommended-grade integration today.

Avoid if

Avoid high-impact or sensitive production use unless the documented authentication, permissions, rollback, and data handling match your environment.

Trade-offs

Hosted relay plus real-machine filesystem/shell authority and current beta status are not suitable for broad Recommended recommendation.

Evidence scope

Evidence

Current source snapshot

Popularity

No MCP-specific repository metric is stored

No MCP-specific package metric is stored

Package identity: @wonderwhy-er/desktop-commander

Stars observed October 21, 2026 · Downloads observed October 21, 2026

Repository evidence: no_public_exact_hosted_implementation_repo. Not MCP-specific/comparable for MCP-server adoption. No attributable public stars metric was verified. Hosted service is current but closed-source. The public remote-desktop-commander repository contains manifests/docs/issues rather than server implementation; `@wonderwhy-er/desktop-commander` is the paired device agent/local project, not the hosted backend. Preserve high-impact machine/file/shell/process risk and OAuth/device-revocation semantics.

Package evidence: adjacent_device_agent. Not MCP-specific/comparable for MCP-server adoption. No attributable public download metric was verified. Hosted service is current but closed-source. The public remote-desktop-commander repository contains manifests/docs/issues rather than server implementation; `@wonderwhy-er/desktop-commander` is the paired device agent/local project, not the hosted backend. Preserve high-impact machine/file/shell/process risk and OAuth/device-revocation semantics.

Maintenance

Publisher activity observed October 21, 2026

Current source snapshot

Trust review

Source relationship: First-party MCP

Reviewed October 21, 2026

Sources

GitHub repository — desktop-commander/remote-desktop-commander ↗

Supporting evidence (2)

Evidence source ↗GitHub repository — wonderwhy-er/DesktopCommanderMCP ↗

Evidence-backed setup

Install & Agents

Choose your MCP client. A client connects to the MCP server; the language model is selected inside that client. Only stored, source-backed configurations are shown.

Claude Code

Transport not recorded

Publisher documented

Pair the machine using dashboard-provided `npx @wonderwhy-er/desktop-commander@latest remote`; add `https://mcp.desktopcommander.app/mcp` as remote Streamable HTTP connector and complete OAuth.

The publisher provides client-specific setup instructions.

Verify safely: Official setup test: ask the assistant to list files on the paired machine; success proves the relay/device path works.

Uninstall and revoke

Dashboard can Revoke one device or Revoke All; Ctrl+C stops the device agent and ends reachability; also remove the MCP connector from the client.

Evidence & methodology

Publisher-documented setup is not the same as MCP100 execution testing. “MCP100 logic checked” means the stored configuration shape was reviewed, not that third-party MCP software was run.

Evidence checked 2026-09-20T00:00:00.000Z

Evidence 1 ↗

Reviewed setup

Type-appropriate, source-backed setup for this mcp server profile.

Endpoint: https://mcp.desktopcommander.app/mcp
Setup notes: Source rechecked October 21, 2026: Official hosted Remote Desktop Commander MCP service. Lifecycle: current active beta hosted closed source. Hosted service is current but closed-source. The public remote-desktop-commander repository contains manifests/docs/issues rather than server implementation; `@wonderwhy-er/desktop-commander` is the paired device agent/local project, not the hosted backend. Preserve high-impact machine/file/shell/process risk and OAuth/device-revocation semantics.

Read additional publisher installation details

From the publisher README

Publisher installation details

Original client setup and configuration retained from the publisher documentation.

View original README ↗

Publisher-documented clients

Claude CodeClaude DesktopCursorGemini CLIVS Code

These names appear in the publisher's installation documentation. MCP100-verified configurations are shown separately above when available.

Quick start

1. Start the device agent

On the computer you want to control:

npx @wonderwhy-er/desktop-commander@latest remote

Your browser opens to a verification page showing a pairing code (also printed in the terminal — a standard OAuth device-flow check). Sign in, confirm the codes match, and the terminal reports "Device ready". Keep the agent running: close the terminal, no access.

2. Connect your AI client

Each client walks you through OAuth sign-in on first connect.

claude.ai / Claude Desktop — Settings → Connectors → Add custom connector, then enter:

https://mcp.desktopcommander.app/mcp

Claude Code:

claude mcp add --transport http remote-desktop-commander https://mcp.desktopcommander.app/mcp

(If you work inside a checkout of this repo, Claude Code also picks up the included .mcp.json automatically.)

ChatGPT — Settings → Apps & Connectors → Advanced settings → enable Developer mode (requires a plan that includes it), then Create connector and enter:

https://mcp.desktopcommander.app/mcp

Cursor — one click: Add to Cursor. Or add to ~/.cursor/mcp.json manually:

{
  "mcpServers": {
    "remote-desktop-commander": {
      "url": "https://mcp.desktopcommander.app/mcp"
    }
  }
}

VS Code — install the agent plugin (bundles this server):

copilot plugin install desktop-commander/remote-desktop-commander

Or add the server directly to .vscode/mcp.json in your workspace (or your user-level mcp.json):

{
  "servers": {
    "remote-desktop-commander": {
      "type": "http",
      "url": "https://mcp.desktopcommander.app/mcp"
    }
  }
}

Gemini CLI:

gemini extensions install https://github.com/desktop-commander/remote-desktop-commander

3. Try it

These work against any machine running the agent, no setup needed:

"List the contents of my home directory and tell me what's there."

"Create a folder called ai-test in my Documents folder. Inside it, write a short Python script that prints the date, and run it."

"Start a Python REPL on my machine, import pandas, and tell me which version is installed. Keep the session alive."

"Search my home directory for files modified in the last 24 hours and group them by folder."

Full walkthrough with troubleshooting: docs/SETUP.md

Loading optional publisher installation details…

Show source-catalog configuration

Pair the machine using dashboard-provided `npx @wonderwhy-er/desktop-commander@latest remote`; add `https://mcp.desktopcommander.app/mcp` as remote Streamable HTTP connector and complete OAuth.

Read publisher documentation

Publisher documentation

Publisher README

Original product, capability, tool, and usage documentation from the MCP publisher. Installation sections appear under Install & Agents.

View original README ↗

Remote Desktop Commander

Build, explore, automate on your computer — from anywhere.

Reach your computer's filesystem and terminal from any AI app that supports remote MCP connectors. Remote Desktop Commander is a hosted MCP server that relays a secure connection to your real machine, giving your AI assistant the same full file and shell access as the local server — without you needing to be at the keyboard.

Server endpoint: https://mcp.desktopcommander.app/mcp (Streamable HTTP, OAuth 2.0)
Dashboard: mcp.desktopcommander.app
Status: currently in beta
Demo: watch the video

This repository hosts the public manifests, documentation and issue tracker for the hosted service. The service implementation is not open source. For the open-source local (stdio) server, see DesktopCommanderMCP.

What you can do

Build from scratch — create features and applications with simple commands
Manage development environments — set up servers, configure systems, handle processes
Explore existing codebases — navigate and understand complex repositories
Edit documents in place — work on Word, Excel, and PDF files where they live on disk
Manage context and documentation — keep track of project details and technical specifications
Control multiple machines — pair several computers and address them by name in one conversation

Requirements

Node.js 18 or newer (for npx) on each computer you want to control
One terminal running the device agent per machine
Works on macOS, Windows, and Linux

Available tools

Category	Tools
Read & explore	Read File, Read Multiple Files, List Directory, Get File Info
Search	Start Search, Get More Search Results, Stop Search, List Active Searches
Write & edit	Write File, Edit File Block, Move or Rename File, Create Directory, Write or Modify PDF
Terminal & processes	Start Process, Send Input to Process, Read Process Output, List Active Sessions, List System Processes, Terminate Session, Kill System Process
Devices & account	List Paired Devices, Current User Info, Ping Device, Shutdown Device Agent
Configuration & help	Get Configuration, Set Configuration Value, Get Prompt Library, Get Recent Tool Activity, Get Usage Statistics, Submit Feedback

How it works

sequenceDiagram
    participant AI as AI app (web, mobile, desktop)
    participant S as mcp.desktopcommander.app
    participant D as Your computer (device agent)
    AI->>S: MCP tool call (OAuth 2.0 bearer)
    S->>D: relayed to your paired device
    D->>D: executes locally
    D->>S: result
    S->>AI: MCP response

Authentication is standard OAuth 2.0 with PKCE; devices pair via the OAuth device authorization flow (the short-code approval you see at setup).
The server only accesses data explicitly requested through tool calls; transmission is encrypted in transit (HTTPS/TLS).
A machine is reachable only while its device agent is running — stop it with Ctrl+C and access ends. Devices can also be reviewed and revoked at any time from the dashboard.
Tools execute with your user account's permissions on the paired machine, so treat your connected AI accounts like credentials and protect them with MFA. Read the full trust model in SECURITY.md.

Support & legal

Setup guide: docs/SETUP.md
Bugs & feature requests: GitHub Issues · Contributing: CONTRIBUTING.md
Community: Discord
Security reports: see SECURITY.md
Privacy policy: Remote Desktop Commander privacy policy · Terms of service: legal.desktopcommander.app
License: LICENSE — this repository holds docs and manifests only; the hosted service is proprietary

DesktopCommanderMCP — the open-source local MCP server (npm: @wonderwhy-er/desktop-commander), which also ships the remote device agent used for pairing
desktopcommander.app — product site

Loading optional publisher documentation…

FAQ

Is this an official MCP?

github:desktop-commander is listed as First-party MCP in MCP100’s current evidence.

Current official resources:

Publisher documentation ↗

Quick start

1. Start the device agent

On the computer you want to control:

npx @wonderwhy-er/desktop-commander@latest remote

2. Connect your AI client

Each client walks you through OAuth sign-in on first connect.

claude.ai / Claude Desktop — Settings → Connectors → Add custom connector, then enter:

https://mcp.desktopcommander.app/mcp

Claude Code:

claude mcp add --transport http remote-desktop-commander https://mcp.desktopcommander.app/mcp

(If you work inside a checkout of this repo, Claude Code also picks up the included .mcp.json automatically.)

ChatGPT — Settings → Apps & Connectors → Advanced settings → enable Developer mode (requires a plan that includes it), then Create connector and enter:

https://mcp.desktopcommander.app/mcp

Cursor — one click: Add to Cursor. Or add to ~/.cursor/mcp.json manually:

{
  "mcpServers": {
    "remote-desktop-commander": {
      "url": "https://mcp.desktopcommander.app/mcp"
    }
  }
}

VS Code — install the agent plugin (bundles this server):

copilot plugin install desktop-commander/remote-desktop-commander

Or add the server directly to .vscode/mcp.json in your workspace (or your user-level mcp.json):

{
  "servers": {
    "remote-desktop-commander": {
      "type": "http",
      "url": "https://mcp.desktopcommander.app/mcp"
    }
  }
}

Gemini CLI:

gemini extensions install https://github.com/desktop-commander/remote-desktop-commander

3. Try it

These work against any machine running the agent, no setup needed:

"List the contents of my home directory and tell me what's there."

"Create a folder called ai-test in my Documents folder. Inside it, write a short Python script that prints the date, and run it."

"Start a Python REPL on my machine, import pandas, and tell me which version is installed. Keep the session alive."

"Search my home directory for files modified in the last 24 hours and group them by folder."

Full walkthrough with troubleshooting: docs/SETUP.md

Best for

Not ideal for

Avoid if

Trade-offs

Evidence

Popularity

Maintenance

Trust review

Sources

Install & Agents

Claude Code

Reviewed setup

Publisher installation details

Quick start

1. Start the device agent

2. Connect your AI client

3. Try it

What it does

Representative uses

Important limits

Context Footprint

Access & risk

Other options

Context7 MCP

Docker MCP Gateway

GitHub MCP

Publisher README

Remote Desktop Commander

What you can do

Requirements

Available tools

How it works

Support & legal

Related

FAQ

Publisher installation details

Quick start

1. Start the device agent

2. Connect your AI client

3. Try it

Publisher README

Remote Desktop Commander

What you can do

Requirements

Available tools

How it works

Support & legal

Related