PlanToCode vs MCP Replay

PlanToCode for iOS connects to PlanToCode Desktop so you can work with the same local projects and coding-agent sessions from iPhone, Mac, or Windows. Open PlanToCode Desktop and enable Mobile access. Then add a project, create a session, send instructions, inspect files, and review diffs from iPhone. Continue the same work in either app. PlanToCode uses the OpenAI/Codex account and subscription you connect. Your existing OpenAI/Codex plan supplies coding-agent access; PlanToCode does not bundle or replace it. Use iPhone and desktop to work with the same projects and sessions: - Add a project from a folder on the connected desktop - Create a coding-agent session or open an existing one - Continue workspace chat with text, dictation, queued follow-ups, and completion alerts - Pick model and reasoning settings for supported sessions - Browse project files from the selected desktop - Preview Markdown, Mermaid diagrams, media, files, and git diff details - Review git changes and patch details - Open agent notifications directly into the matching desktop, project, session, and agent chat - See reconnect state when the desktop or network changes How it works: 1. Install and open PlanToCode Desktop from https://plantocode.com/downloads on your Mac or Windows computer. 2. Sign in on desktop and iOS with the same account and region. On desktop, enable Mobile access. 3. Pick the connected desktop in the iOS app. Add or select a project, then create or open a session. 4. Work in either app and continue the same project and session on the other. The desktop runs the agent and owns access to local repositories. The iOS app creates and controls projects and sessions through the authenticated PlanToCode relay. Requirements: - PlanToCode Desktop on your host computer - Internet connectivity for account and device relay Review generated changes and AI output before using them. Terms of Service: https://plantocode.com/terms Privacy Policy: https://plantocode.com/privacy

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.