mobile-mcp

An MCP Server for Android running on the phone, optmized for token usage, supports also files downloads, camera, a privacy mode (to anonymize/pseudononymize your PII) and support various tunnelling (included a free E2E HTTPS tunnel out of the box in addition to cloudflare and ngrok).

PhonePi MCP enables seamless integration between desktop AI tools and your smartphone, providing 23+ direct actions including SMS messaging, phone calls, contact management, snippet creation and search, clipboard sharing, notifications, battery status checks, and remote device controls.

Qmcp is a powerful, cross-platform AI chat client built with Flutter, implementing the Model Context Protocol (MCP) for intelligent, context-aware interactions with multiple LLMs.

A secure native Android MCP server: use phone capabilities through MCP without a computer, ADB, or cloud backend.

AI agent skill that autonomously experiences mobile apps and generates structured product reports (UX analysis, user manuals, optimization suggestions)

Control panel for VLLM

Mobile MCP AI context pack for Claude Code, Codex, Cursor, and Aider: AGENTS.md, CLAUDE.md, prompts, evals, pitfalls, and verification notes for mobile-next/mobile-mcp.

Framework-grounded app teardown system for Claude Desktop. 10 modules, 5 personas, India consumer context. Built by Palash Somani.

This project integrates Cucumber BDD, Claude Code, and MobileWright MCP to enable AI-assisted, behavior-driven mobile application testing and automation. It combines natural-language test scenarios, intelligent code generation, and MCP-powered mobile interaction for efficient end-to-end testing.