remcp

Securely control paired computers with ReMCP: semantic desktop UI/Accessibility, browser DOM/CDP, keyboard and pointer input, files, terminals, diagnostics…

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • List Devices: Use this when the target computer is not already unambiguous. Call it first to list computers paired to the signed-in ReMCP account and see which ones are online.
  • Manage Account: Use this when the task concerns the signed-in ReMCP account or paired-computer membership: inspect profile, recent calls, usage or hosted configuration; create a pairing; or ping, rena
  • Read File: Use this when the task calls for plain text files on a paired computer: source code, configuration, Markdown, logs, scripts, or other line-oriented text. Use read_document instead for PDF,

What data it sees

Do you need an account

No: the server works without sign-in

Securely control paired computers with ReMCP: semantic desktop UI/Accessibility, browser DOM/CDP, keyboard and pointer input, files, terminals, diagnostics, screenshots, and structured PDF/DOCX/XLSX tools.

How to connect

How to connect remcp to Claude

The server address to paste into Claude settings:

https://remcp--antonbaider.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect remcp to ChatGPT

The server address to paste into ChatGPT settings:

https://remcp--antonbaider.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect remcp to Cursor

The server address to paste into Cursor settings:

https://remcp--antonbaider.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (10)

Raw names from tools/list. Only developers need these.

list_devicesUse this when the target computer is not already unambiguous. Call it first to list computers paired to the signed-in ReMCP account and see which ones are online.
manage_accountUse this when the task concerns the signed-in ReMCP account or paired-computer membership: inspect profile, recent calls, usage or hosted configuration; create a pairing; or ping, rename, enable, disable, or permanently remove one pairing. Use list_devices first when the target computer is ambiguous. Local runtime preferences belong to manage_system.
read_fileUse this when the task calls for plain text files on a paired computer: source code, configuration, Markdown, logs, scripts, or other line-oriented text. Use read_document instead for PDF, DOCX, XLSX and other structured document content. read_file keeps legacy PDF/DOCX extraction for compatibility but should not be the model’s first choice for those formats.
manage_filesUse this when the task is about files, directories, archives, or filesystem search on one paired computer. Choose exactly one operation; parameters must contain only that operation’s arguments and are validated against its closed schema. Write, edit, move, permission, and delete operations can change or remove local data or fail on OS permissions, while read and search operations leave files unchanged. Use read_file instead for one known text file so the native file preview remains available.
run_terminalUse this when the task needs a shell command or an existing ReMCP terminal session: start, read, wait, interact, stop, or list sessions. Choose exactly one operation; parameters are validated against that operation’s closed schema. Starting or interacting with commands can change local or external state, and force termination can lose unsaved process work; reading, waiting, and listing do not mutate the session. Use manage_system for OS-wide process inventory or killing an arbitrary PID.
control_computerUse this when the task needs semantic inspection or control of native desktop applications: snapshots, windows, accessibility/UI elements, waits, displays, app launch, text/input, clipboard, open/reveal, notifications, or short screen recording. Semantic snapshot/find/wait operations observe state, while clicks, typing, window close, app launch, clipboard writes, and recording can change application or local state. Prefer semantic inspection/actions before raw coordinates; use view_image only when pixels are required and control_browser for page DOM/CDP actions.
view_imageUse this when the result must be pixels from a paired computer: read an existing image, capture the desktop, or capture one window, monitor, or region. These operations return pixels without interacting with the visible UI; use control_computer or control_browser instead when semantic structure or an action is enough.
control_browserUse this when the target is a debuggable Chromium page and the task needs tabs, navigation, DOM/accessibility inspection, element search/actions, waits, or explicit JavaScript evaluation. Snapshot, find, and wait operations observe page state; navigation, clicks, typing, uploads, and JavaScript evaluation can change page or remote-site state. Choose one operation and pass only its validated parameters. Use control_computer for browser chrome or other native desktop/non-CDP applications.
manage_systemUse this when the task concerns operating-system or ReMCP runtime state: system/runtime/process facts, runtime preferences, services, event logs, networking, installed apps, environment, audio, or explicit power actions. Fact, log, and inventory operations only observe state; process termination, runtime preference changes, service/audio changes, restart, and shutdown can interrupt work or change the machine. Choose one operation and pass only its validated parameters. Use run_terminal for general shell commands and ReMCP terminal sessions.
manage_documentsUse this when the task is structured document content: read PDF/DOCX/XLSX, edit DOCX/XLSX directly, or merge, split, extract, or inspect PDFs. DOCX/XLSX edits can replace the input when no separate output is supplied, and PDF write operations create or replace their requested output; read_document itself is read-only. Choose one operation and pass only its validated parameters. Use read_file for plain line-oriented text and control_computer only for interactive Office UI.