PhonePi MCP: Turn your phone into a toolbox for AI assistants using Model Context Protocol
LocalAbout PhonePi MCP: Turn your phone into a toolbox for AI assistants using Model Context Protocol
PhonePi MCP is an MCP server that lets Claude, Cline, Cursor and other AI apps control a smartphone through a companion mobile app. It is aimed at users who want desktop AI tools to act on phone functions, and requires the phone and computer to share a network.
Key features
- 01Send SMS messages and make phone calls
- 02Manage contacts
- 03Send notifications and set timers and alarms
- 04Copy text to the phone clipboard
- 05Check battery level and make the phone beep
- 06Command-line management with start, stop, status and restart
Use cases
- 01Asking an AI assistant to send a test notification to a phone
- 02Sending text messages or placing calls from a desktop AI tool
- 03Locating a misplaced phone or checking its battery through an assistant
MCP support
The project is an MCP server that exposes phone control functions to MCP clients such as Claude, Cline and Cursor, with the companion mobile app carrying out the actions.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
22Saved tool list · updated 3w ago
This tool takes no parameters.
Details
From the project READMEPhonePi MCP
A MCP server that lets you control your phone from your favorite AI apps!
Prerequisites
You need to setup the PhonePi MCP app on your phone. Please visit PhonePi MCP for instructions.
MCP Server Setup
Simply follow the steps below to setup the server in your favorite AI apps such as Claude, Cline or Cursor.
Installation
Install the package globally:
npm install -g phonepi-mcp
Or run directly with npx:
npx phonepi-mcp
Setup
Simply add the following MCP config to your AI app:
{
"mcpServers": {
"phonepi-mcp": {
"command": "npx",
"args": [
"phonepi-mcp",
"start"
]
}
}
}
Save the file with the above settings. This is all you need for your setup besides the mobile app.
Connecting
- Ensure your phone and your desktop are on the same network. Using something like Tailscale is recommended for convenience, but it's optional.
- Enter the local ip address and port (11041) in the companion mobile app to connect to the server.
- Once everything's connected correctly, you can simply start asking your AI assistant to do stuff! For example, try asking it to send a test notification to your phone.
MCP server management cli (Optional)
Standalone usage
The setup instructions above is all you need for setting it up with respect to MCP clients like Cline, Claude Desktop etc.
But, PhonePi MCP also provides a standalone command-line interface for you to manage the MCP server from outside the clients.
Commands
start: Start the MCP serverstop: Stop the running MCP serverstatus: Check if the MCP server is runningrestart: Restart the MCP server
Starting the Server
phonepi-mcp start
Options:
-p, --port <port>: Specify the port to run the server on (default: 11041)-b, --background: Run the server in the background
Example:
phonepi-mcp start -p 8080 -b
Checking Server Status
phonepi-mcp status
Stopping the Server
phonepi-mcp stop
Restarting the Server
phonepi-mcp restart
Options:
-p, --port <port>: Specify the port to run the server on (default: 11041)-b, --background: Run the server in the background
Connecting Your Phone
- Install the PhonePi MCP app on your phone
- Start the server on your computer using
phonepi-mcp start - In the app, connect to your computer's IP address and port (default 11041)
Features
- Remote phone control via MCP protocol
- Get battery level
- Send SMS messages
- Make phone calls
- Find your phone by making it beep
- Set timers and alarms
- Copy text to clipboard
- Manage contacts
- Send notifications
Development
Build the package:
npm run build
Run in development mode:
npm run dev
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.