Edit Android preferences using adb and Node.js.
Unlock the power of natural language for Android app development with the Android Preference Editor MCP Server. Effortlessly edit user preferences in real time using simple, conversational commands—no manual file editing required! Built on the robust Android Preference Editor library, this server seamlessly connects with MCP (Model Context Protocol) clients to supercharge your AI-driven workflows.
Just tell the MCP server what you want to do, for example:
Experience a smarter, faster way to manage Android preferences—just ask!
Name | Description |
---|---|
change_preference | Changes the value of an existing preference |
delete_preference | Delete an existing preference |
add_preference | Adds a new preference given the name, value, and type |
read_preferences | Reads all user preferences in a file |
devices | Lists connected Android devices |
list_apps | Lists apps installed on the device |
list_files | Lists preference files for an app |
Toggle a user preference | Available tools | Add a preference |
---|---|---|
![]() | ![]() | ![]() |
See more demos in the demo screenshots directory
v1.0.41+
)This server is available in the Docker MCP Catalog. Enable the Pref Editor server in Docker desktop's MCP toolkit and you'll have access to all the available tools.
Assumes an MCP compatible client is installed.
Add the following configuration to the MCP server config file. For example, for the GitHub Copilot IntelliJ Plugin, the config file is ~/.config/github-copilot/intellij/mcp.json
.
{
"servers": {
"pref-editor": {
"command": "docker",
"args": ["run", "-i", "--rm", "charlesmuchene/pref-editor-mcp-server"]
}
}
}
{
"servers": {
"pref-editor": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@charlesmuchene/pref-editor-mcp-server"]
}
}
}
Add this server to the /Users/<username>/Library/Application Support/Claude/claude_desktop_config.json
configuration file.
{
"mcpServers": {
"pref-editor": {
"command": "docker",
"args": ["run", "-i", "--rm", "charlesmuchene/pref-editor-mcp-server"]
}
}
}
{
"mcpServers": {
"pref-editor": {
"command": "npx",
"args": ["-y", "@charlesmuchene/pref-editor-mcp-server"]
}
}
}
You can troubleshoot problems by tailing the log file:
tail -f ~/Library/Logs/Claude/mcp-server-pref-editor.log
To use the server with VS Code, you need to:
mcp.json
or settings.json
:.vscode/mcp.json
{
"servers": {
"pref-editor": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@charlesmuchene/pref-editor-mcp-server"]
}
}
}
~/Library/Application Support/Code/User/settings.json
{
"mcp": {
"pref-editor": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@charlesmuchene/pref-editor-mcp-server"]
}
}
}
For more information, see the VS Code documentation.
Refer to DEV.md for instructions on how to build this project.
You can use the MCP Inspector for visual debugging of this MCP Server.
npx @modelcontextprotocol/inspector npm run start
See LICENSE
For questions or support, reach out via GitHub Issues.
We welcome contributions from the community! 🎉
First-time contributors: Please start by reading our CONTRIBUTING.md guide, which covers:
For detailed development instructions, see DEV.md.
Predict anything with Chronulus AI forecasting and prediction agents.
Advanced code search and transformation powered by ugrep and ast-grep for modern development workflows.
Create, validate, and render diagrams from D2 (Declarative Diagramming) code into SVG and PNG formats.
Introspects Laravel codebases to provide structured information about views, routes, classes, and models using the mateffy/laravel-introspect package.
Interact with Odoo instances using the XML-RPC API. Requires configuration via environment variables or config files.
A server for Zero-Vector's hybrid vector-graph persona and memory management system, featuring advanced LangGraph workflow capabilities.
A minimal MCP server mock in TypeScript for testing MCP clients, supporting both STDIO and HTTP/SSE protocols.
Bootstrap Model Context Protocol (MCP) servers and clients in TypeScript with best practices, examples, and proper tooling setup.
A framework for AI-powered command execution and a plugin-based tool system. It can be run as a standalone service or embedded in other projects to expose a consistent API for invoking tools and managing tasks.
A quantum circuit simulator with noise models and OpenQASM 2.0 support, accessible via the Model Context Protocol (MCP).