A side-by-side look at the Remote Pc MCP and Agent Droid Bridge MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Remote Pc MCP for os automation work; choose Agent Droid Bridge for os automation as a local process. You can also run both side by side in one mcpServers block.
REMOTE_PC_MCP_TOKEN.shell_exec, read_file, write_file.ADB_EXECUTION_MODE, ADB_ALLOW_SHELL, ADB_PATH, ADB_EXTRA_TOOL_PACKS, MCP_LOG_ENABLED, MCP_LOG_DIR.get_ui_hierarchy, tap_screen, swipe_screen.Rows where the two servers differ are marked.
| Spec | R Remote Pc MCP | |
|---|---|---|
| Category | OS Automation | OS Automation |
| Quality signal | 49/100 · Fair | 57/100 · Good |
| Install command | Not confirmed yet | Confirmed |
| Transport | — | Local subprocess (stdio) |
| Auth | API key required | No auth required |
| Pricing | Free | Free |
| Required env vars | REMOTE_PC_MCP_TOKEN | ADB_EXECUTION_MODEADB_ALLOW_SHELLADB_PATHADB_EXTRA_TOOL_PACKSMCP_LOG_ENABLEDMCP_LOG_DIR |
| Verified owner | Community listing | Community listing |
| GitHub stars | 6 | 22 |
| Directory activity | 0 views 0 installs 0 upvotes | 3 views 0 installs 0 upvotes |
| Tools | 15 | 14 |
| Full listing | View Remote Pc MCP | View Agent Droid Bridge |
shell_execRun any shell command — returns stdout, stderr, exit coderead_fileRead a file as text or base64 (binary fallback)write_fileWrite text or binary content to a filelist_directoryList files and directories, optionally recursivesystem_infoOS, CPU, RAM, and GPU stats (NVIDIA GPUs via `nvidia-smi`; absent on non-GPU hosts)start_processStart a long-running command in the background — returns a PIDget_process_outputPoll stdout/stderr of a background process by PIDkill_processTerminate a process by PIDdownload_fileDownload a URL directly to this machinetake_screenshotCapture the primary display — returns base64-encoded PNGclickClick at screen coordinates `(x, y)` — left / right / middle, single or multi-clickmove_mouseMove cursor to `(x, y)`, optionally animatedget_ui_hierarchyReturns the current Android screen as an XML UI hierarchy.
Use this when you need to locate element coordinates, read text, or find resource IDs to
interact with. Do not call this after every action — only call it when you actually need to
read screen content. To check if the screen changed after an action, use snapshot_ui before
the action and detect_ui_change after.tap_screenA tap gesture at the given pixel coordinates on the Android screen.swipe_screenA swipe gesture on the Android screen from (x1,y1) to (x2,y2) over the given duration.type_textText input into the currently focused Android input field.
Spaces are encoded automatically.press_keyA key event sent to the Android device using the given keycode integer.take_screenshotA PNG screenshot of the current Android device screen with width, height,
and base64-encoded image data.list_devicesAll Android devices currently visible to ADB, with their serial numbers,
connection state, and model names.launch_appAn Android app launched by its component name (package/activity).execute_adb_commandThe output of an ADB command. Parsed safely via shlex and never passed to a system shell.snapshot_uiTakes a lightweight snapshot of the current UI state and returns a short token.
Use this before performing an action (tap, swipe, launch, key press) when you only need to
confirm the screen changed afterward — not read its content. Pass the returned token to
detect_ui_change as baseline_token. This avoids loading the full XML hierarchy into context
unnecessarily. Do not use this when you need to read or interact with screen elements — use
get_ui_hierarchy for that.detect_ui_changePolls the UI hierarchy after an action and returns when the screen content changes or the
timeout is reached. Returns changed status and elapsed time. By default, omits the XML
hierarchy for efficiency — set return_hierarchy=True to receive the full hierarchy.
For efficient change detection: call snapshot_ui before the action, perform the action, then
call detect_ui_change with baseline_token. Only use without baseline_token when you need to
wait for a slow transition (loading screens, animations). Do not use to read the current
screen state — use get_ui_hierarchy for that.get_screen_elementsStructured list of UI elements currently visible on the Android screen.
Returns elements filtered and shaped by the chosen mode. Prefer 'tappable' for
navigation and 'interactive' when you need XPath or bounds for ADB commands.
Only use 'all' as a last resort — it returns every node and can be large.Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
No confirmed install command for Remote Pc MCP yet — follow the setup steps linked from its listing page rather than a guessed package name.
{
"mcpServers": {
"neverlow512-agent-droid-bridge": {
"command": "uvx",
"args": [
"agent-droid-bridge"
],
"env": {
"ADB_EXECUTION_MODE": "YOUR_ADB_EXECUTION_MODE_HERE",
"ADB_ALLOW_SHELL": "YOUR_ADB_ALLOW_SHELL_HERE",
"ADB_PATH": "YOUR_ADB_PATH_HERE",
"ADB_EXTRA_TOOL_PACKS": "YOUR_ADB_EXTRA_TOOL_PACKS_HERE",
"MCP_LOG_ENABLED": "YOUR_MCP_LOG_ENABLED_HERE",
"MCP_LOG_DIR": "YOUR_MCP_LOG_DIR_HERE"
}
}
}
}