Official Remote Control: Architecture & Data Flow

⏱ Est. reading time: 3 min Updated on 5/7/2026

Understanding the architecture helps in troubleshooting and evaluating security.

Component Topology

flowchart TB
    subgraph LocalMachine[Local Machine]
      CLI[Claude Code CLI]
      WS[WebSocket Client]
      CLI --- WS
    end
    subgraph Anthropic[Anthropic Backend]
      Bridge[Remote Control Bridge]
      Auth[OAuth / JWT]
      Push[Push Service]
    end
    subgraph Clients[Remote Clients]
      Web[claude.ai/code Web]
      App[iOS / Android App]
    end
    WS <-->|WebSocket + Polling| Bridge
    Bridge --- Auth
    Bridge --> Push
    Web --- Bridge
    App --- Bridge

Key Data Flows

  1. Inbound: Client Input → Bridge → Local CLI → Tool/Model.
  2. Outbound: Model Token Stream → Local CLI → Bridge → Real-time rendering on Client.
  3. Permissions: Tool execution requests (Bash, Edit) are pushed to the client for approval.
  4. State: Files, Git, and Shell remain strictly local. Only transcripts are mirrored to the cloud.

Note: v2.1.69 optimized the polling frequency from 1-2 seconds to once every 10 minutes when stable, reducing server load by 300x.

Related Tools & Resources

Related Products

📦

mempalace

MemPalace is a local-first AI memory tool designed to store conversation history verbatim and retrieve it through semantic search, without summarizing or paraphrasing. It utilizes a structured index, categorizing information into "wings," "rooms," and "drawers" to enable scoped searches. The retrieval layer is pluggable (ChromaDB by default), ensuring all data remains on the user's machine unless opted out. It achieves an impressive 96.6% R@5 raw recall on the LongMemEval benchmark, notably without requiring LLMs or API calls, showcasing high performance in a local environment.
📦

code-review-graph

code-review-graph is an AI-assisted code review tool that builds a structural map of code using Tree-sitter and incrementally tracks changes to provide precise context to AI assistants via the Model Context Protocol (MCP). This approach significantly reduces token consumption by enabling AI models to read only the minimal set of files relevant to a change, rather than the entire codebase. It aims to solve the token waste problem in large repositories and monorepos, improving the efficiency and quality of AI code reviews.
📦

claude-context

Claude Context is an MCP (Model Context Protocol) plugin developed by Zilliztech, designed to provide deep code context to Claude Code and other AI coding assistants. It leverages semantic search to efficiently retrieve relevant code snippets from entire codebases, injecting them directly into the AI's context. This approach addresses the limitations of context windows and high costs associated with large codebases by storing the codebase in a vector database for efficient management and cost-effectiveness.