Install
openclaw skills install remote-clawsFull remote desktop control of a machine via Remote Claws MCP. Use when asked to: take a screenshot of the remote desktop; click, type, or drag with the mouse/keyboard on the remote machine; run commands or scripts; automate a Chromium browser on the remote machine; read or write files on the remote machine.
openclaw skills install remote-clawsControls a remote machine over MCP/SSE. All 39 tools are provided by the remote-claws MCP server registered in openclaw.json.
Use Remote Claws tools whenever you need to interact with the remote desktop machine — taking screenshots, clicking buttons, typing text, running commands, automating a browser, or transferring files. If the user asks you to do something "on the remote machine" or "on Windows," these are your tools.
desktop_screenshot to see what's on screen. Use the coordinates from the screenshot to target actions.browser_* tools use CSS selectors and are resolution-independent. Only use desktop_* tools for web tasks if the browser tools can't reach something (e.g. browser dialogs, file pickers).desktop_click_element and desktop_get_element_text target UI controls by name — more reliable than coordinate clicking, which breaks when windows move.exec_run starts a command and returns immediately. Use exec_get_output with wait=true if you need to block until it finishes.desktop_screenshot — capture full screen or region [x, y, width, height]desktop_mouse_click — left/right/middle click at x, ydesktop_mouse_move — move cursor to x, ydesktop_mouse_drag — drag from start to end coordinatesdesktop_type_text — type ASCII text at current focus (ASCII only)desktop_press_key — press key or combo: "enter", "ctrl+c", "alt+f4"desktop_scroll — scroll at x,y; direction "up" or "down"desktop_find_window — find windows by title or class_name substringdesktop_focus_window — bring window to foreground by titledesktop_list_elements — list UI controls (buttons, fields) inside a windowdesktop_click_element — click a named UI element (more reliable than coords)desktop_get_element_text — read the value of a named UI elementbrowser_navigate — go to a URLbrowser_click — click element by CSS selectorbrowser_fill — set input value (handles Unicode, triggers change events)browser_type — type keystroke-by-keystroke (appends, does not clear)browser_press_key — key press e.g. "Enter", "Control+a"browser_get_text — extract visible text from element (default: body)browser_get_html — get HTML markup of elementbrowser_eval_js — run JavaScript in page contextbrowser_screenshot — screenshot page or elementbrowser_wait_for — wait for element state: visible/hidden/attached/detachedbrowser_select_option — select a dropdown option by value or labelbrowser_go_back / browser_go_forwardbrowser_tabs_list / browser_tab_new / browser_tab_closeexec_run — start command; returns process_id immediatelyexec_get_output — read stdout/stderr; set wait=true to blockexec_send_input — send a line to stdin of a running processexec_kill — terminate a processexec_list — list all tracked processesfile_write — write base64 content to a pathfile_read — read file as base64 (use offset/limit for large files)file_list — list directory; supports glob patterns, recursivefile_delete — delete file or empty directoryfile_move — move or rename file/directoryfile_info — get size, created, modified timestampsThe remote-claws MCP server requires a bearer token, configured in openclaw.json when registering the server. The server will reject unauthenticated connections with 401.
The server also supports IP allowlisting (allowed_ips), host header validation (allowed_hosts), and per-tool permission policies (permissions.json) to restrict which tools are available. See the setup guide and README for configuration details.
desktop_type_text is ASCII only. For Unicode, use browser_fill or clipboard: exec_run powershell Set-Clipboard, then desktop_press_key ctrl+v.