Claude Code: Remote Control Expands to More Users
Claude CodeClaude Code's Remote Control feature — which lets developers continue a local CLI session from any phone, tablet, or browser via claude.ai/code or the Claude mobile app — has been expanded to a broader set of users. Remote Control keeps all execution local while syncing the conversation across devices, supports automatic reconnection when a laptop sleeps or network drops, and works with the full local environment including MCP servers, tools, and project configuration. The feature is available as a research preview on Max plans, with Pro plan support coming soon.
Sources & Mentions
5 external resources covering this update
Anthropic just released a mobile version of Claude Code called Remote Control
VentureBeat
Claude Code Remote Control
Simon Willison
Anthropic's Remote Control feature brings Claude Code to mobile devices
Help Net Security
Anthropic reveals Remote Control, a mobile version of Claude Code
TechRadar
Claude Code now lets you handle tasks remotely from a phone
Digital Trends
Continue Local Sessions From Any Device
Claude Code's Remote Control feature has been expanded to a broader user base, making it available to more developers on Max plans as part of its ongoing research preview rollout. Remote Control allows developers to continue a local Claude Code session from their phone, tablet, or any browser — picking up exactly where they left off without interrupting local execution.
The feature works through claude.ai/code and the Claude mobile app on both iOS and Android. When a developer starts a Remote Control session, Claude keeps running locally on their machine the entire time — the remote device is simply a window into that local session. This means the full local environment remains available: filesystem access, MCP servers, tools, and project configuration all stay active.
How It Works
Starting a Remote Control session requires running claude remote-control from the project directory, or typing /rc within an existing Claude Code session. The terminal generates a unique session URL and a QR code (toggleable via spacebar) that can be scanned from a phone for instant access.
Once connected, the conversation stays in sync across all devices — developers can send messages from their terminal, browser, and phone interchangeably. If a laptop sleeps or the network drops, the session reconnects automatically when the machine comes back online, making it resilient to the interruptions that are common in mobile workflows.
For developers who want Remote Control active on every session without manually invoking it each time, the /config command offers an "Enable Remote Control for all sessions" toggle.
Security Model
Remote Control makes outbound HTTPS requests only and never opens inbound ports on the developer's machine. All traffic travels through the Anthropic API over TLS — the same transport security as any standard Claude Code session. The connection uses multiple short-lived credentials, each scoped to a single purpose and expiring independently.
Remote Control vs Claude Code on the Web
While both Remote Control and Claude Code on the web use the claude.ai/code interface, the key difference is execution location. Remote Control runs on the developer's machine, preserving access to local MCP servers, tools, and project configuration. Claude Code on the web runs in Anthropic-managed cloud infrastructure, suited for tasks that don't require a local environment.
Current Availability
Remote Control is available as a research preview on Max plans. Pro plan support has been announced as coming soon. The feature is not yet available on Team or Enterprise plans. Each Claude Code instance supports one remote session at a time.