Give Cline an Android phone: a hosted Android MCP server for Cline.
Set it up
1. Get a key. Paste this into Cline. It installs the Phonebox CLI and signs you in from the terminal, so you never paste a key into the chat. Then put the key in your environment with export PHONEBOX_API_KEY=$(phonebox token).
Read https://phonebox.dev/setup.md and set me up with Phonebox from here: get me signed in and ready, then find out what I want to use phones for and help me with that.2. Add the server. In the Cline panel, open MCP Servers, then Configure, then Configure MCP Servers, and add the entry. Set type to streamableHttp: without it, Cline assumes the older SSE transport. Cline expands ${env:PHONEBOX_API_KEY} from the environment VS Code was started with.
{
"mcpServers": {
"phonebox": {
"type": "streamableHttp",
"url": "https://phonebox.dev/mcp",
"headers": { "Authorization": "Bearer ${env:PHONEBOX_API_KEY}" },
"disabled": false
}
}
}3. Check it. Open MCP Servers in the Cline panel. You should see phonebox with 13 tools. list_phones is a safe first call: it only reads.
What Cline can do with the phone
| Task | Tools |
|---|---|
| Get a phone | create_phone, list_phones, get_phone, start_phone |
| See the screen | observe: numbered text elements with labels, plus a screenshot |
| Use apps | act: up to 20 taps, types, swipes and key presses per call |
| Install your build | create_app_upload, complete_app_upload, install_app, list_apps |
| Hand off to a person | live_view_url: a link to watch and control the phone |
| Stop paying | park_phone; reboot_phone when an app hangs |
Cline reads the screen as text, so it taps “Sign in” by its label instead of guessing coordinates. Phonebox never retries a write to the phone on its own, so a slow response can't turn into a double order. A parked phone is free and keeps its apps, files and sign-ins. A running one costs $0.06 a minute, billed per second, and new accounts get $2 of credit with no card.
A first task
Build the debug APK and install it on my Phonebox phone.
Walk through the onboarding and settings screens I changed in this branch.
Read the screen before every action. Report anything that looks broken,
with the screen text you saw. Park the phone when you finish.Other agents
The same server works in Claude Code, Codex, Cursor, Gemini CLI, Windsurf and GitHub Copilot. See the Android MCP server guide for every tool, and cloud phones for AI agents for the bigger picture.
Questions
Can Cline control an Android phone?
Yes. Add Phonebox's hosted MCP server to cline_mcp_settings.json with type streamableHttp, url https://phonebox.dev/mcp and an Authorization header. Cline gets 13 tools to create a cloud Android phone, read the screen, act, install APKs, hand off to a person and park the phone.
Why does Cline need type streamableHttp?
Cline treats a remote server without a type as the legacy SSE transport. Phonebox's server speaks Streamable HTTP, so set type to streamableHttp.
What does it cost?
$0.06 per phone-minute while the phone runs, billed per second. Parked phones are free and keep their apps and sign-ins. New accounts get $2 of credit with no card.