---
title: "Discussion on \"Let Claude Code operate remote computers as if they were local (Codex and Gemini CLI too)\" | Hashnode"
description: "Discussion on \"Let Claude Code operate remote computers as if they were local (Codex and Gemini CLI too)\". Remote shell scripts across networks, mounted remote projects, screenshots and port forwarding, by machine ID"
url: "https://hashnode.com/posts/let-claude-code-operate-remote-computers-as-if-they-were-local-codex-and-gemini-cli-too/6aff034130de0d9687fe3a91"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Let Claude Code operate remote computers as if they were local (Codex and Gemini CLI too)](https://rockdesk.hashnode.dev/let-claude-code-operate-remote-computers-as-if-they-were-local-codex-and-gemini-cli-too?utm_source=hashnode&utm_medium=feed)

Remote shell scripts across networks, mounted remote projects, screenshots and port forwarding, by machine ID

1d ago · 7 min read · rockdesk.hashnode.dev  
Read the article

-   [#ai](https://hashnode.com/tag/ai)
-   [#ai-agents](https://hashnode.com/tag/ai-agents)
-   [#claude-code](https://hashnode.com/tag/claude-code)
-   [#mcp](https://hashnode.com/tag/mcp)
-   [#remote-desktop](https://hashnode.com/tag/remote-desktop)

## Written by

[RockDesk](https://hashnode.com/@rockdesk)

@rockdesk

  
[View profile](https://hashnode.com/@rockdesk)

Remote desktop, terminal, files and VPN by machine ID, and your AI agent can use it too.

RockDesk gives every computer you own a 9-digit ID: remote desktop, terminal, files and VPN, peer-to-peer with no ports to open. AI agents such as Claude Code, Codex and Gemini CLI can use it through the rds command line or MCP. https://rockdesk.io

## Responses 1

Markdown supported · ⌘↵ to post

[Seedance AI](https://hashnode.com/@seedance-ai)

[1d ago](https://hashnode.com/posts/let-claude-code-operate-remote-computers-as-if-they-were-local-codex-and-gemini-cli-too/6aff034130de0d9687fe3a91/comment/6aff0b2cc2cbe8a06874ea38)

Giving CLI coding agents transparent access to remote hosts without changing their local tool-calling mental model removes a lot of friction. The key guardrail is keeping per-host command scoping and explicit session visibility so you always know which box a destructive command targets.
