ai-dashboad/flutter-skill

AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero config. Works with Claude, Cursor, Windsurf, Copilot. Test Flutter, React Native, iOS, Android, Web, Electron, Tauri, KMP, .NET MAUI — all from natural language.

What it solves

It eliminates the need to write and maintain brittle end-to-end (E2E) test code (like Page Objects or XPath selectors). Instead, it allows AI agents to interact with running applications using natural language, enabling autonomous testing, bug discovery, and UI exploration across multiple platforms without manual script writing.

How it works

The project provides an MCP (Model Context Protocol) server and SDKs that connect AI agents (such as Claude, Cursor, or Copilot) directly to an app's runtime. Rather than relying solely on expensive screenshots, it uses the browser's Accessibility Tree to provide the AI with a compact semantic summary of the page, reducing token usage by 87-99%. The agent can then execute a wide array of tools—such as tapping, typing, and scrolling—via the MCP server or an HTTP REST API.

Who it’s for

Developers and QA engineers who want to automate application testing across mobile, web, and desktop platforms using AI agents instead of traditional testing frameworks.

Highlights

  • Multi-Platform Support: Works across 10 platforms including Flutter, React Native, Electron, Tauri, Android, iOS, Web, and .NET MAUI.
  • AI-Native Integration: Fully compatible with MCP-enabled agents like Claude Desktop, Cursor, Windsurf, and VSCode Copilot.
  • Token Efficiency: Uses semantic accessibility trees instead of images to lower LLM costs and improve understanding.
  • Extensive Toolset: Offers over 250 tools for interaction, visual regression, network mocking, API testing, and accessibility audits.
  • High Performance: Direct runtime communication allows operations like tapping to execute in 1-2ms.

Related

  • Project
    leancodepl/marionette_mcp

    An MCP server that enables AI agents to inspect and interact with running Flutter applications for automated smoke testing and interaction.

  • Project
    alumnium-hq/alumnium

    An AI-native library and MCP for end-to-end testing that allows users to perform actions and verify assertions in applications using natural language.

  • Project
    Arenukvern/mcp_flutter

    A Dart MCP server and Flutter package that lets AI agents inspect and drive running Flutter apps, enabling a closed feedback loop for debugging and UI development.

  • Project
    AlexGladkov/claude-in-mobile

    `mcp-devices` (aka `claude‑in‑mobile`) is a modular Node/Rust server that lets Claude‑style AI agents control Android, iOS, web, desktop, Aurora, and HarmonyOS devices. Install the base (`npm i -g mcp-devices`), add platform plugins (e.g., `@mcp-devices/plugin-android`), enable them, and point an MCP‑compatible client at the server. The tool provides actions like screenshots, taps, UI inspection, live debugging, and testing, enabling AI‑driven device automation and embodied‑agent research.

  • Project
    callstack/agent-device

    A tool and MCP server that allows AI coding agents to inspect, control, and verify mobile and desktop apps across multiple platforms to create a live feedback loop for development.