Phone MCP is a Python-based server that enables AI assistants to control Android phones through ADB commands. Developed by hao, it provides tools for making calls, sending text messages, taking screenshots, recording screens, managing contacts, launching apps, and retrieving system information. The implementation includes specialized modules for different phone functionalities and supports map-related features when an API key is configured. It's particularly useful for scenarios requiring remote phone control, automated testing, or accessibility assistance, allowing AI agents to interact with mobile devices without direct physical manipulation.
No reviews yet. Be the first to review!
Sign in to join the conversation
Make a call to the specified phone number. Parameters: phone number (string)
End the current call.
Send an SMS to the specified phone number with the given message. Parameters: phone number (string), message (string)
Get received messages with pagination. Parameters: --limit (integer)
Get sent messages with pagination. Parameters: --limit (integer)
Get contacts with pagination. Parameters: --limit (integer)
Create a new contact with the specified name and phone number using UI automation. Parameters: name (string), phone number (string)
Take a screenshot of the current screen.
Record the screen for a specified duration. Parameters: --duration (integer)
Launch the specified application by its name. Parameters: app name (string)
Launch the specified application using an alternative method. Parameters: app name (string)
Close the application specified by its package name. Parameters: package name (string)
List installed apps with basic info or detailed info and pagination. Parameters: --page (integer), --page-size (integer), --detailed
Launch a specific activity by its package and activity name. Parameters: package name (string), activity name (string)
Open a URL in the device's default browser. Parameters: URL (string)
Analyze the current screen and provide structured information about UI elements.
Perform various screen interaction actions like tap, swipe, input text, etc. Parameters: action (string), parameters (dictionary)
Search for nearby points of interest with phone numbers based on location. Parameters: coordinates (string), keywords (string), radius (integer)
Monitor UI for changes with various options like waiting for elements to appear or disappear. Parameters: --interval (float), --duration (integer), --watch-for (string), --text (string), --id (string), --class-name (string), --raw