Search packages, repositories and app categories

Package detailsv0.7.0

marionette_flutter

Flutter extensions for AI agent interaction via MCP — lets Claude, Copilot, and Cursor tap, scroll, type, and screenshot your app.

AndroidiOSWebmacOSWindowsLinux
30-day downloads
250K
Likes
77
Pub points
160

Install package

flutter pub add marionette_flutter

Package Overview

Package selection guidance compiled from public package information, community data, and project usage.

Marionette Flutter enables AI agents to interact with Flutter apps through the MCP protocol, allowing tools like Claude, Copilot, and Cursor to perform actions such as tapping, scrolling, typing, and capturing screenshots. It extends Flutter applications with capabilities for automated testing and AI-driven UI interaction, enhancing development workflows. The package integrates seamlessly across multiple platforms including Android, iOS, Web, macOS, Windows, and Linux. Designed for developers leveraging LLMs in app testing or automation, it bridges the gap between AI agents and native app behaviors.

Use cases

  • Automated UI testing with AI agents
  • AI-powered app exploration and debugging
  • Integration with Copilot and Claude for app interaction
  • Real-time screenshot capture during testing
  • Cross-platform app interaction via MCP

Key features

  • MCP protocol support for AI agent communication
  • Support for tap, scroll, type, and screenshot actions
  • Multi-platform compatibility (Android, iOS, Web, macOS, Windows, Linux)
  • Seamless integration with LLM-powered development tools
  • Lightweight Flutter extensions for agent interaction

Suitable for

  • Developers using AI agents for testing
  • Teams implementing AI-driven UI automation
  • Flutter projects requiring advanced test orchestration
  • Integrators working with Copilot, Claude, or Cursor
  • Projects focused on generative AI in app development

Considerations

  • Requires compatible AI agent with MCP support
  • May need additional setup for secure agent access
  • Limited to platforms where MCP is supported
  • Depends on external AI tooling for full functionality
  • Not intended for production user interactions

Original README

Original README snapshot from the linked source repository. Visit the repository for the latest content.

marionette_mcp

Marionette MCP

License marionette_mcp pub.dev badge

"Playwright MCP/Cursor Browser, but for Flutter apps"

Marionette MCP enables AI agents (Claude Code, Copilot, Cursor, Gemini CLI, and more) to inspect and interact with running Flutter applications. It connects your AI agent directly to a running app via the Model Context Protocol (MCP), so it can see the widget tree, tap elements, enter text, scroll, and capture screenshots for automated AI-driven smoke testing and interaction.

Marionette MCP keeps the surface area intentionally small. It exposes only a handful of high-signal actions and returns the minimum actionable data, which helps keep prompts focused and context sizes under control.

Learn more about Marionette MCP:

Demo

Marionette MCP vs Flutter MCP

The official Dart & Flutter MCP server focuses on development-time tasks: searching pub.dev, managing dependencies, analyzing code, and inspecting runtime errors. It can also drive the UI, but it does so through Flutter Driver, which introduces extra instrumentation in your app. Marionette MCP focuses solely (and in an opinionated way) on runtime interaction: tapping buttons, entering text, scrolling, and taking screenshots, while requiring minimal changes to your app. Use Flutter MCP to build your app, use Marionette MCP to test and interact with it with minimal code changes.

Quick Start

[!NOTE] Your Flutter app must be prepared to be compatible with Marionette. The steps below are the short version — the Getting Started guide walks through each one.

  1. Prepare your app — add marionette_flutter and initialize MarionetteBinding in main.dart:

    flutter pub add marionette_flutter
    
    void main() {
      if (kDebugMode) {
        MarionetteBinding.ensureInitialized();
      } else {
        WidgetsFlutterBinding.ensureInitialized();
      }
      runApp(const MyApp());
    }
    
  2. Install the bridge — activate the MCP server (for the CLI alternative, see the CLI guide):

    dart pub global activate marionette_mcp
    
  3. Configure your AI tool — e.g. for Claude Code:

    claude mcp add --transport stdio marionette -- marionette_mcp
    

    Other tools (Cursor, Gemini CLI, Copilot, Antigravity): see Configuring your AI tool.

  4. Run your app in debug mode — flutter run, then copy the VM service URI from the console (e.g. ws://127.0.0.1:9101/ws).

  5. Connect and interact — ask your agent to connect using that URI and start driving the app.

[!IMPORTANT] Standard Material widgets work out of the box. If your app uses a custom design system, configuration is required — otherwise the agent can't see or tap your custom buttons and fields. Start with the Production Setup Checklist.

What you can do

Once connected, an agent can drive your app with a small, focused toolset: inspect the widget tree (get_interactive_elements), tap / secondary_tap / double_tap / long_press / swipe / pinch_zoom / scroll_to, enter_text, press_back_button, take_screenshots, read get_logs, and hot_reload. Full list: MCP Tools.

Your app can also expose its own actions to the agent via Custom Extensions — navigate by route name, seed test data, toggle feature flags, and more.

Some real-world prompts:

"I implemented the Forgot Password screen — connect, navigate to login, tap 'Forgot Password', enter a valid email, submit, and check the logs that the API call fired."

"I refactored the routing. Run a smoke test: cycle through all bottom-nav tabs and verify each screen loads without exceptions in the logs."

"Investigate the unresponsive 'Clear Cache' button on Settings — find it via get_interactive_elements, tap it, and analyze the logs."

Documentation

Guide What's inside
Getting Started Zero-to-driving in 5 steps.
Flutter Setup The binding, debug-only init, the single-binding rule.
Configuration Custom design systems, production checklist, complete main.dart.
Log Collection Wire up get_logs (logging, logger, or custom).
Semantics Make custom-painted / rich content readable to agents.
MCP Tools Full tool reference + AI-tool configuration.
Custom Extensions Expose app-specific actions as agent tools via registerMarionetteExtension.
CLI Drive Marionette from any shell-capable agent.
Troubleshooting Common gotchas and limitations.

Packages

Package Role
marionette_flutter The binding you add to your Flutter app. Required.
marionette_mcp MCP server bridging AI agents to your running app.
marionette_cli CLI alternative for shell-only / restricted environments.
marionette_logging LogCollector adapter for the logging package.
marionette_logger LogCollector adapter for the logger package.

🛠️ Maintained by LeanCode

This package is built with 💙 by LeanCode. We are top-tier experts focused on Flutter Enterprise solutions.

Why LeanCode?
  • Creators of Patrol – the next-gen testing framework for Flutter.

  • Production-Ready – We use this package in apps with millions of users.

  • Full-Cycle Product Development – We take your product from scratch to long-term maintenance.


Need help with your Flutter project?

👉 Hire our team   •   Check our other packages

Categories

Dependencies

Dependency list 2 items

Source repository

Projects using this package