The Rebind MCP server wraps the remote-control protocol as Model Context Protocol tools, so an AI agent can drive a real keyboard and mouse: take a screenshot, reason about it, click, type, and run Luau — all as genuine USB HID. Because the OS sees a real device, it works in any application, including ones that block synthetic input. It runs against the same remote.luau server as everything else in this section — the MCP server is just another client, built for agents instead of programs.

Install

--selftest connects to the running Rebind relay and captures the screen, then exits — run it first to confirm the server is reachable before wiring up an agent. It needs remote.luau running (see Run the server).

One command, every client

add-mcp writes the correct config for whichever clients you name — Claude Code, Cursor, Codex, OpenCode, VS Code, Windsurf, Zed, and more — in each one’s native format:
Drop -a <agent> for the clients you want, or pass --all. -g installs globally; omit it to write project-local config. Restart the client afterward so it picks up the new server.

Any MCP client

The server speaks MCP over stdio. Point any MCP-capable client (Claude Desktop, an IDE, your own agent) at it manually:
Set REBIND_TOKEN when the relay has an auth token (the Auth token field in remote.luau’s settings panel).

OpenClaw

The @usinput/rebind-computer-use skill on ClawHub teaches an OpenClaw agent when and how to use these tools, with a built-in safety policy for irreversible actions.
Then start a new OpenClaw session — skills are snapshotted at session start, so one installed mid-session stays invisible until you restart.

Tools

The skill’s policy leans on run_lua for deterministic sequences and reserves screenshots for genuine visual reasoning — a screenshot-per-action loop costs tokens quadratically, since every image is re-sent on every later turn.

Telemetry

Set REBIND_AGENT_LOG=<path> to append one JSONL line per tool call ({ts, tool, ok, latency_ms, note}) — no screenshot bytes, no user content. Off unless set. Useful for measuring which tools fail and how many actions a task takes.