Agent Ready

RemoteCommander MCP server✓

Vu Van Minh Quang·Live in

Connect chat to your PCs

A smarter, harnessed agent that works on your computer — your files and its memory stay on your devices. RemoteCommander connects your AI to a machine you control, so the chat can read and edit files, run commands and manage long-running programs, then note where the work stands so the next chat picks up where this one left off.

ChatGPT rank
#13,894of 15,719 · top 89%
▼ Fell 244 places in 1 days, from #13,650
Tools
8
Read3
Change1
Destructive4

What you can ask

What can you do on my computer?

RemoteCommander

Follows the skill

Connect RemoteCommander to your AI app

Claude

  1. Open Add custom connector ↗
  2. Name it RemoteCommander and paste the URL
  3. Click Add, then sign in to your account
https://rc.rentaicoder.com/mcp

Gemini, Grok and other MCP clients

https://rc.rentaicoder.com/mcp

Details

Sign-in

Type
OAuth
Before sign-in
Every tool needs it
Provider
Its own
App registration
✓ Dynamic registration✓ CIMD

Server

Host
rc.rentaicoder.com
Tool list from
The store listing
Protocol
Unknown, needs sign-in

Capabilities

Interactive UI
✓ Yes
Server instructions
✓ Yes
Skills
✓ 2
Skills over MCP
Unknown
Prompts
Unknown
ChatGPT plugin events
Unknown
MCP notifications
Unknown

In the stores

ChatGPT
App created Oct 2, 2026
ChatGPT directory
Productivity #3470

Server instructions

The AI reads these server instructions before using this connector, every time. From the ChatGPT store listing.

RemoteCommander runs on the user's machine and keeps your memory there. Start every conversation with op=recall (pass the user's words as hint), then op=roots. Memory opens one level at a time and every line names the next call: recall alone is the index; recall project=<name> opens a project's open threads (with its standing instructions); recall thread=<key> attaches this chat to a thread and returns what it needs to continue; search query=<words> finds any detail across everything you wrote. End every reply with op=checkpoint: it shows the user what ran and tells you what ended or is still open. Nothing is hidden, only folded: open what the conversation needs, no more. Working in a folder attaches the chat to that project and the result tells you its threads. Tools: (files, op-based), (one bounded command, argv array; if the default soft wait is exceeded it may return the same child as a process_handle), (long-running/interactive programs via a stable process_handle), (durable notes across conversations: write what the next conversation will need — tasks, summaries, conventions), (what ran, durable process endings, and the end-of-reply checkpoint), (read-only troubleshooting guidance for known agent footguns). If exec returns exit=running, continue that exact child with process read/status and do not rerun the command. If an error carries Doctor recovery guidance, call with the supplied symptom before inventing a workaround. A normal child process exit != 0 is not by itself a Doctor problem. When newer authoritative state clearly supersedes a model-created note, summary or task, use the authoritative state and op=forget the stale record once its id is known. When a canonical repository SSOT owns volatile values such as prices, quotas, versions or deployment state, remember the SSOT pointer instead of copying those current values into memory; never auto-forget instructions or approvals merely because they are old. Skills: the user keeps playbooks on this machine as folders with a SKILL.md; recall lists their names and descriptions. When a request matches one, read <dir>/SKILL.md with fs before doing the work and follow it; files it names are relative to that folder. Paths stay inside the workspace roots when any are configured (fs op=roots shows them and the base for relative paths); commands follow local policy; denials explain which policy applied. Other computers: shows each one and its open threads; pass deviceId to any tool to work there, and to op=recall thread= to continue a thread on it. A computer's memory and skills are reachable only while it is online; moving work to another computer is an explicit copy of the summary when the user asks.

Tools

2 skills

RemoteCommander MCP server: questions and answers

What is the RemoteCommander MCP server?

Connect chat to your PCs. A smarter, harnessed agent that works on your computer — your files and its memory stay on your devices. RemoteCommander connects your AI to a machine you control, so the chat can read and edit files, run commands and manage long-running programs, then note where the work stands so the next chat picks up where this one left off.

How do I connect RemoteCommander to ChatGPT?

Open its listing in the app's connector directory and connect. Sign in to your account in the browser window that opens. It uses OAuth, so the AI never sees your password. Step-by-step setup for each app is on this page.

  • In ChatGPT: open the RemoteCommander listing ↗, select Connect, then sign in
  • In any other app: add a custom connector with the URL https://rc.rentaicoder.com/mcp

What is the RemoteCommander MCP server URL?

The RemoteCommander MCP server URL is https://rc.rentaicoder.com/mcp. Paste it as a custom connector in Claude, ChatGPT, Gemini or Grok, or add it to Claude Code, Cursor or any MCP client. Setup steps.

  • Sign-in: OAuth

Does Vu Van Minh Quang have an official MCP server?

Yes. RemoteCommander is published or run by Vu Van Minh Quang, so it is the official MCP server. See other official connectors.

Which AI apps can I use the RemoteCommander MCP server in?

It is listed in 1 store: ChatGPT. Apps where it is not listed can usually still add it as a custom connector.

How popular is the RemoteCommander MCP server?

It is ranked 13,894 of 15,719 in the ChatGPT directory. A rank is the store's own order, not a usage count. How we track ranks.

What tools does the RemoteCommander MCP server have?

It has 8 tools: 3 read data, 1 change data and 4 can delete or overwrite data. See every tool and its inputs.

  • Doctor
  • What ran
  • List computers
  • Agent memory
  • Run a command
  • Filesystem

Can the RemoteCommander MCP server change or delete my data?

Yes. 1 tool can change data and 4 tools can delete or overwrite it. Most AI apps ask before they run these. The store marks these as destructive:

  • Run a command
  • Filesystem
  • Long-running process
  • Transfer file

What skills does the RemoteCommander MCP server have?

It comes with 2 skills. A skill tells the AI how to do one job well with these tools. Read each SKILL.md.

  • Environment troubleshooting xs3: Diagnose ChatGPT-side generic tool refusals separately from RemoteCommander, device and rate-limit errors; verify effects and recover authorized tasks through supported, permitted interfaces.
  • Remote execution: Use when a task needs filesystem, command, or process work on a computer connected through RemoteCommander, including cross-conversation continuation.

What can I do with the RemoteCommander MCP server?

Here are examples from its store listing. Type one into your AI after you connect.

  • What can you do on my computer?

Does the RemoteCommander MCP server show interactive UI in the chat?

Yes. Some of its tools show an interactive widget in the chat, not only text. See more connectors with interactive UI.

How can I track RemoteCommander's rank and tool changes?

This page updates every day. To ask about RemoteCommander from Claude, ChatGPT or a coding agent, connect the Agent Ready MCP server: it tracks ranks, tools and new listings across the AI plugin stores.