Flutter Maestro MCP
F

Flutter Maestro MCP

This is an experimental MCP server that allows AI agents to interact with running Flutter applications through the VM service and execute Maestro automated testing processes.
2.5 points
4.3K

What is the Flutter Maestro MCP Server?

This is a bridge server that connects AI assistants with Flutter applications. Through it, AI can operate Flutter applications like a real human tester: click buttons, enter text, view the interface structure, take screenshots, etc., and can also write and run automated test scripts.

How to use the Flutter Maestro MCP Server?

First, you need to run a Flutter application and obtain its VM Service connection address, then connect through the MCP server. After a successful connection, AI can use various tools to operate the application, check the interface, or run automated tests.

Applicable scenarios

Suitable for scenarios that require AI assistance in Flutter application testing, interface exploration, and automated process execution. For example: let AI automatically test new features, explore the application interface structure, record user operation processes, etc.

Main features

Real-time application connection
Connect to a running Flutter application for real-time interactive operations
Interface structure inspection
Get the UI hierarchy of the application and view the properties and positions of all controls
Interactive operations
Basic user operations such as clicking, entering text, and scrolling
Screen capture
Capture a screenshot of the current application interface
Maestro automation
Write and execute Maestro automated testing processes
Hot reload
Trigger the hot reload of the Flutter application without restarting
Advantages
Real-time interaction: Directly operate a running Flutter application
No code modification required: Connect through the VM Service without additional configuration
AI-friendly: Designed for AI assistants, providing a structured operation interface
Automation integration: Supports the Maestro automated testing framework
Development efficiency: Quickly test and verify interface functions
Limitations
Requires a running application: The Flutter application must be started first
Connection complexity: Manually obtain and enter the VM Service URI
Experimental nature: The functions may be unstable or subject to change
Dependent on external tools: Maestro CLI needs to be installed
Platform limitation: Mainly targeted at Flutter mobile applications

How to use

Install dependencies
Ensure that the Dart environment and Maestro CLI are installed. You can install Maestro via Homebrew: brew install maestro
Configure the MCP server
Add server configuration in the MCP settings of VS Code and specify the path to the Dart script
Start the Flutter application
Run the Flutter application and copy the VM Service URI. You can debug and run it in VS Code or use 'flutter run' in the command line
Connect to the application
Use the 'connect' tool and enter the complete VM Service URI (including the authentication token)
Start interaction
After a successful connection, you can use various tools to operate the application, check the interface, or run tests

Usage examples

Automated login test
Let AI automatically complete the login process test of the application
Interface exploration
Understand all operable elements on the current application interface
Create an automated test script
Generate a Maestro automated test script based on the current operations

Frequently Asked Questions

How to obtain the VM Service URI?
Why does the connection fail?
What is Maestro? Is it necessary to install it?
Can any Flutter application be operated?
Is this tool safe?

Related resources

Maestro official documentation
Installation and usage guide for the Maestro automated testing framework
Flutter development documentation
Official development documentation for the Flutter framework
MCP protocol description
Official specification of the Model Context Protocol
GitHub repository
Source code and latest updates of this project

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
5.6K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
4.2K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
4.8K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
5.1K
4 points
P
Paperbanana
Python
7.3K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
5.8K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
6.6K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
7.7K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.4K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
72.2K
4.3 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
24.6K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
35.5K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
64.5K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
31.2K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.1K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
48.0K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase