Sandbox Relay vs MCP Replay

For developers who run Claude Code or Codex in Docker Sandbox, Sandbox Relay is the phone client for driving that agent. It is a companion, not a standalone app: it needs a broker you run, with an agent connected behind it. Kick off a task from the train, check on a long-running job from the couch, or steer the agent while you are away from your desk. Docker Sandbox runs each agent in its own isolated micro VM. A small broker you self-host sits in the middle: you send work from your phone, the broker passes it to the agent, and the streamed reply comes back. Your infrastructure, your agent. The app is just the remote. New to this setup? The app's support page explains how it works and what you need to run it. WHAT YOU CAN DO - Connect to your broker with a URL and a bearer token. Connections use HTTPS, with plain HTTP allowed only for local-network addresses. - See every connected agent at a glance, with live online/offline status. - Send the agent work and watch its reply stream in token by token. Stop a turn mid-stream, or start a fresh thread whenever you want. - When an agent goes offline, its thread stays readable as history. - See per-turn input and output token counts when the broker reports them. - Save reusable prompts as local notes, organised by hierarchical tags like #work/project/feature. Drill down by tag, copy a note straight into a thread, or link a note to the thread it came from. Notes live on your device only; they never touch the broker. WHAT YOU NEED - A broker you run, reachable from your phone (over your local network, or remotely through a tunnel or private network you control). - A coding agent, Claude Code or Codex, running in Docker Sandbox and connected to that broker. PRIVACY Sandbox Relay talks only to the broker you configure. Your access token is stored securely on your device and sent only to that broker, to authenticate you; it never goes to the developer or any third party. Your notes stay on your device and are never sent anywhere. No third-party analytics, no account to create. Note that the app streams whatever your agent outputs, verbatim.

MCP Replay is a trace viewer for the Model Context Protocol, the open standard AI agents use to call tools. Record a session with the free mcp-tape command line tool, then open it on your phone: every request, response, error, and latency, organized and searchable. WHAT YOU CAN DO - Open .jsonl traces from Files, AirDrop, or any share sheet - Follow a replay link someone sent you, or paste a bare share ID - Watch a live session streaming from mcp-tape on your own network - See paired tool calls with latencies, and per-tool stats (count, errors, avg, p95) - Filter the timeline by tool or method - Share a trace as a link that expires after 30 days, with a delete token so you stay in control BUILT FOR PRIVACY Traces stay on your phone. Nothing is uploaded unless you explicitly share a trace, and there are no accounts, no analytics, and no tracking. Live mode connects directly to your own computer; the stream never touches a server. FOR ANYONE BUILDING WITH AGENTS If you use Claude, ChatGPT, or any MCP-compatible agent framework and have ever asked "what did it actually do?", this is the answer. Record with one command: npx mcp-tape -- your-mcp-server-command Then open the trace here or at mcpreplay.dev. MCP Replay is open source and independent. It works with any tool that emits the open mcp-tape trace format.