erius-phone-mcp
An MCP server that turns your
ERIUS PHONE device into native tools for Claude Code,
Claude Desktop, Cursor, or any other MCP client. An ERIUS PHONE device is a real
Android phone or tablet dedicated to your agent. Once this server is connected,
your agent can:
- list its devices
- read the screen as an accessibility tree or a screenshot
- tap, long-press, type, swipe and scroll
- launch and stop apps, open URLs and send intents
- install and uninstall APKs
- pull crash logs
The agent drives the device directly. You don't write any glue code.
Early access: this package is pre-1.0 (0.2.0). Tool names and
arguments may still change before 1.0.
Requirements
Install
Option A: uvx (no install step). If you have
uv, your MCP client can launch the server with
uvx erius-phone-mcp. uv fetches the package and keeps it in its own
environment. The client configs below show this form.
Option B: pip, into its own virtual environment so its dependencies
don't clash with your other Python projects:
python3 -m venv ~/.venvs/erius-phone-mcp
~/.venvs/erius-phone-mcp/bin/pip install erius-phone-mcp
This installs an erius-phone-mcp command at
~/.venvs/erius-phone-mcp/bin/erius-phone-mcp. Use that absolute path as
the command in your client config: GUI apps such as Claude Desktop and Cursor
usually don't see your venv's PATH. python -m erius_phone_mcp does the same
thing as running the command.
Configuration
The server is configured entirely through environment variables:
| Variable | Required | What it is |
|---|
ERIUS_PHONE_API_KEY | yes | Your ERIUS PHONE API key. Every request is authenticated with it and scoped to your account. |
ERIUS_PHONE_DEFAULT_DEVICE | no | The device id to use when a tool call doesn't name one (e.g. vanilla). Without it, the agent passes device on each call; list_devices shows the ids. |
ERIUS_PHONE_API_URL | no | API base URL. Default https://api.eriusphone.com; only set it if we gave you a different one. |
ERIUS_PHONE_TIMEOUT | no | HTTP timeout per request, in seconds. Default 30. |
Getting an API key
Request access at https://eriusphone.com. During early access the ERIUS
PHONE team sets up each account by hand. You'll receive your API key and
device id(s) directly from us. If you signed up and haven't heard back, email
info@eriusphone.com. The same key signs you in to the dashboard at
https://eriusphone.com/dashboard/, which shows your devices live.
Treat the key like a password: anyone who has it can control your device.
Important: MCP clients start this server as a subprocess, and they
generally do not pass along variables you export in your shell. Put
the variables in the client's env block, as shown below.
Add it to your MCP client
In every example, replace the key and device id with your own. If you
installed with pip instead of using uvx, replace "command": "uvx", "args": ["erius-phone-mcp"] with "command": "/home/you/.venvs/erius-phone-mcp/bin/erius-phone-mcp".
Claude Code
claude mcp add erius-phone \
-e ERIUS_PHONE_API_KEY=your-api-key \
-e ERIUS_PHONE_DEFAULT_DEVICE=your-device-id \
-- uvx erius-phone-mcp
Add -s user to make the server available in all your projects, or
-s project to write it to a shared .mcp.json. Don't commit your key to a
shared .mcp.json. Claude Code expands ${VAR} references in that file, so
you can keep the key in an environment variable instead:
{
"mcpServers": {
"erius-phone": {
"command": "uvx",
"args": ["erius-phone-mcp"],
"env": {
"ERIUS_PHONE_API_KEY": "${ERIUS_PHONE_API_KEY}",
"ERIUS_PHONE_DEFAULT_DEVICE": "your-device-id"
}
}
}
}
Run /mcp inside Claude Code to check that erius-phone is connected.
Claude Desktop
Edit claude_desktop_config.json (Settings โ Developer โ Edit Config). On
macOS it's in ~/Library/Application Support/Claude/; on Windows it's in
%APPDATA%\Claude\.
{
"mcpServers": {
"erius-phone": {
"command": "uvx",
"args": ["erius-phone-mcp"],
"env": {
"ERIUS_PHONE_API_KEY": "your-api-key",
"ERIUS_PHONE_DEFAULT_DEVICE": "your-device-id"
}
}
}
}
If Claude Desktop can't find uvx, put its absolute path in command
(which uvx). Fully quit and reopen Claude Desktop after editing.
Cursor
Put the same mcpServers block in ~/.cursor/mcp.json to use it in all
projects, or in .cursor/mcp.json for one project. Then enable erius-phone
under Cursor Settings โ MCP.
Any other MCP client
The server speaks MCP over stdio. Point your client at uvx erius-phone-mcp, or at the erius-phone-mcp executable, and pass the
environment variables above.
Every tool that acts on a device takes an optional device argument. If you
leave it out, the tool uses ERIUS_PHONE_DEFAULT_DEVICE.
Account and devices
| Tool | Description |
|---|
whoami | Which account and key this server is using, and the device ids it can access. A quick way to check the key works. |
list_devices | Every device your key can access, with live status (booted, Android version, screen size). |
get_device | Full status of one device, including the app currently in the foreground. |
Seeing the screen
| Tool | Description |
|---|
snapshot | Accessibility-tree snapshot of the current screen: every visible element with its text, role and a ref you can pass to tap/type/scroll. Refs reset on every snapshot. |
screenshot | The screen as MCP image content, so the model sees it directly. Default: JPEG, longest side 1024 px (tens of KB). format, quality, max_side and scale change that; format="png", max_side=null gives the full-size PNG (about 3 MB on a phone). A text line gives the image and screen sizes. |
foreground | Just the foreground app (package, activity) and whether a crash dialog is showing. |
wait_for_text | Wait until some text appears on screen, up to timeout_ms (max 120000). Returns the snapshot it saw. |
Acting on the screen
| Tool | Description |
|---|
tap | Tap by ref, by visible text/content_desc, or at raw x,y pixels. |
long_press | Long-press by ref, by text/content_desc, or at x,y (optional hold time ms). |
type_text | Type into a field. Can tap a ref/text_target first, clear the field, and press Enter after. |
press_key | back, home, enter, delete, tab, escape, up, down, left, right, space, power, volup, voldown, recent, menu, wakeup, or a numeric keycode. |
swipe | Swipe between two points in device pixels. |
scroll | Scroll a container up/down/left/right. Pass the ref of the ScrollView/List itself, not of a row inside it. |
Apps
| Tool | Description |
|---|
launch_app | Launch an installed app by package name (e.g. com.android.settings). |
open_url | Open an http/https/market URL, optionally in a specific app. |
send_intent | Start an activity with any intent action, e.g. android.settings.WIFI_SETTINGS, with optional data, package, component and extras. |
stop_app | Force-stop an app. |
list_apps | Installed apps; third_party_only=True for user-installed ones only. |
install_apk | Upload and install an APK from a file on the machine running this server. Returns package name, version, and whether the install succeeded. |
uninstall_app | Uninstall an app by package name. |
get_crash_log | The device's crash log buffer (logcat -b crash). Use it after an app crashes to see the real stack trace. |
Quick example
Once the server is connected, ask your agent in plain language, e.g.
"List my ERIUS devices, go to the home screen, and open Contacts." Here's what
happens under the hood. The outputs below are real, lightly trimmed.
1. Find your device. The agent calls list_devices:
{"devices": [
{"id": "vanilla", "description": "redroid Android 13, no Google services", "state": "device",
"bootCompleted": true, "android": "13", "sdk": 33, "screen": {"width": 720, "height": 1280}},
{"id": "tablet1", "form": "tablet", "description": "redroid Android 13 (vanilla, tablet)", "state": "device",
"bootCompleted": true, "android": "13", "sdk": 33, "screen": {"width": 1600, "height": 2560}}
]}
2. Go home and look at the screen. press_key(key="home", device="vanilla")
returns {"ok": true}, then snapshot(device="vanilla") returns the
foreground app plus this tree:
- Group
- ScrollView [ref=1]
- Group
- AppWidgetHostView (Search)
...
- Text [ref=4] "Gallery" (Gallery)
- View (Home)
- Group
- Text [ref=5] "Contacts" (Contacts)
- Text [ref=6] "WebView Browser Tester" (WebView Browser Tester)
- Text [ref=7] "Camera" (Camera)
3. Tap something. tap(device="vanilla", ref="5"), tap(device="vanilla", text="Contacts") and tap(device="vanilla", x=102, y=1116) all open Contacts
and return {"ok": true}. After any action, take a fresh snapshot, because
refs are only valid until the next one.
4. Check the result. foreground(device="vanilla") now reports the
Contacts app, and screenshot(device="vanilla") returns the screen as an
image your agent sees directly.
Installing an APK for QA works the same way:
install_apk(device="vanilla", apk_path="/path/to/app.apk")
โ {"ok": true, "package": "com.erius.dashtest", "versionName": "1.0", "label": "ERIUS Dash Test",
"adbOutput": "Performing Streamed Install\nSuccess", "ms": 94, ...}
Tips and limits
- Errors are passed through. If the API refuses an action, the tool call
fails with the API's error code and message, e.g.
HTTP 404: SelectorNotFound ... nothing on screen matches {"text": "..."} or HTTP 422: no_launcher_activity. The agent can read the message and adjust.
- Typing needs a ready field. Keystrokes sent while a field is still
opening are lost. If tapping a field opens a new screen (as Android
Settings' search does), tap it, wait with
snapshot/wait_for_text, then
call type_text without a target. Check the result with snapshot.
- ASCII-only typing.
type_text supports printable ASCII only (an adb
limitation): no emoji, accented characters or non-Latin scripts.
- Scroll by container.
scroll needs the ref of the scrollable container
(a ScrollView/List line in the snapshot). If the container has no ref,
use swipe.
- Screenshots cost context. The default screenshot is a JPEG with its
longest side at 1024 px (tens of KB). A full-size PNG of a phone
(1440ร3120) is about 3 MB, more than many MCP clients accept in one tool
result. Prefer
snapshot (text, much smaller) and take screenshots only
when you need pixels.
- Coordinates from a scaled screenshot.
x,y are device pixels unless
you pass image_width and image_height (the size of the screenshot you
read them from) to tap, long_press or swipe.
install_apk reads a local file. The path is on the machine running
erius-phone-mcp, not on the phone. The APK is streamed from disk and
uploaded in full on each call.
- One server process = one API key. To use several accounts, add several
server entries with different names and keys.
- Rate limits. The API allows about 30 requests per second per IP and
queues at most 8 requests per device; beyond that you get HTTP 429.
Troubleshooting
ERIUS_PHONE_API_KEY is not set: the variable didn't reach the server
process. Put it in the client's env block, not just your shell. The server
also prints a warning about this on stderr at startup, which shows up in your
client's MCP logs.
no device id given and ERIUS_PHONE_DEFAULT_DEVICE is not set: pass
device= in the tool call or set ERIUS_PHONE_DEFAULT_DEVICE. list_devices
shows your ids.
HTTP 401: the key is wrong or revoked. HTTP 403: the device id doesn't
exist or isn't on your account. Run whoami to see which devices your key
can use.
HTTP 503 device_offline: the device is restarting. Retry shortly.
could not reach the ERIUS PHONE API at ...: the URL is wrong, or the API
is unreachable from your machine. Check ERIUS_PHONE_API_URL, and raise
ERIUS_PHONE_TIMEOUT if you're on a slow link.
License
MIT. The full license text is in the LICENSE file shipped with the package.