Flutter Inspector MCP Server

Integrations

  • Interfaces with Dart VM Service Protocol to access Flutter/Dart process information, retrieve version details, and monitor various event streams for debugging Flutter applications.

  • Connects to a Flutter app's debug mode to extract data about widget trees, render trees, layer trees, and semantics, enabling AI tools to provide context-aware assistance for Flutter app development.

Flutter Inspector MCP Server for AI-Powered Development

GitHub Repository

🔍 Model Context Protocol (MCP) server that connects your Flutter apps with AI coding assistants like Cursor, Claude, Cline, Windsurf, RooCode or any other AI assistant that supports MCP server

See small video tutorial how to setup mcp server on macOS with Cursor - https://www.youtube.com/watch?v=NBY2p7XIass

Note

Since there is a new experimental package in development which exposes Dart tooling development tool actions to clients, maybe in future this project may be not needed that much.

Therefore my current focus is

  1. to stabilize and polish only these tools that will be useful in development (so it would be more plug & play) see more in MCP_RPC_DESCRIPTION.md
  2. find workaround to not use forwarding server.

Hope it will be useful for you,

Have a nice day!

Currently Flutter works with MCP server via forwarding server. Please see Architecture for more details.

⚠️ WARNING ⚠️

Dump RPC methods (like dump_render_tree), may cause huge amount of tokens usage or overload context. Therefore now they are disabled by default, but can be enabled via environment variable DUMPS_SUPPORTED=true.

See more details about environment variables in .env.example.

🚀 Getting Started

🎯 Available tools for AI Agents

Error Analysis

  • get_app_errors [Resource|Tool] - Retrieves precise and condensed error information from your Flutter app Usage:
    • Uses only short description of the error. Should filter duplicate errors, to avoid flooding Agent context window with the same errors.
    • Uses Error Monitor to capture Dart VM errors. Meaning: first, start mcp server, forwarding server, start app, open devtools and extension, and then reload app, to capture errors. All errors will be captured in the DevTools Extension (mcp_bridge).

    Tested on: ✅ macOS, ✅ iOS Not tested on: 🚧 Android, 🤔 Windows, 🤔 Linux, ❌ Web See issue

Development Tools

  • hot_reload [Tool] - Performs hot reload of the Flutter application Tested on: ✅ macOS, ✅ iOS, ✅ Android Not tested on: 🤔 Windows, 🤔 Linux, ❌ Web See issue
  • screenshot [Resource|Tool] - Captures a screenshot of the running application. Configuration:
    • Enable with --images flag or IMAGES_SUPPORTED=true environment variable
    • May use compression to optimize image size

    Tested on: ✅ macOS, ✅ iOS Not tested on: 🚧 Android, 🤔 Windows, 🤔 Linux, ❌ Web See issue

All tools default to using port 8181 if no port is specified. You can override this by providing a specific port number.

📚 Please see more in MCP_RPC_DESCRIPTION

🔧 Troubleshooting

get_app_errors- Since errors are captured in DevTools Extension, you need to make sure that, you have restarted or reloaded Flutter app after starting MCP server, forwarding server and DevTools mcp_bridge extension.

Also make sure you:

  1. Verify that forwarding server is running.
  2. Opened Devtools in Browser.
  3. Have added MCP extension to your Flutter app dev dependencies and enabled it in Devtools.
  4. Connection Issues
    • Ensure your Flutter app is running in debug mode
    • Verify the port matches in both Flutter app and inspector
    • Check if the port is not being used by another process
  5. AI Tool Not Detecting Inspector
    • Restart the AI tool after configuration changes
    • Verify the configuration JSON syntax
    • Check the tool's logs for connection errors

🚧 Smithery Integration 🚧 (work in progress)

The Flutter Inspector is registered with Smithery's registry, making it discoverable and usable by other AI tools through a standardized interface.

Integration Architecture

┌─────────────────┐ ┌──────────────┐ ┌──────────────┐ ┌─────────────────┐ ┌─────────────┐ │ │ │ │ │ │ │ │ │ │ │ Flutter App │<--->│ DevTools │<--->│ Forwarding │<--->│ MCP Server │<--->│ Smithery │ │ (Debug Mode) │ │ Extension │ │ Server │ │ (Registered) │ │ Registry │ │ │ │ │ │ │ │ │ │ │ └─────────────────┘ └──────────────┘ └──────────────┘ └─────────────────┘ └─────────────┘

🤝 Contributing

Contributions are welcome! Please feel free to submit pull requests or report issues on the GitHub repository.

📖 Learn More

📄 License

MIT - Feel free to use in your projects!


Flutter and Dart are trademarks of Google LLC.

You must be authenticated.

A
security – no known vulnerabilities
A
license - permissive license
A
quality - confirmed to work

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

A MCP server with simple goal to debug Flutter apps by giving ability to AI coding assistants (Cline, Cursor, Claude etc..) tools to do analysis of widget trees, navigation, and layout issues. See Architecture to understand how it works https://github.com/Arenukvern/mcp_flutter/blob/main/ARCHITECTURE.md

  1. ⚠️ WARNING ⚠️
    1. 🚀 Getting Started
      1. 🎯 Available tools for AI Agents
        1. Error Analysis
        2. Development Tools
      2. 🔧 Troubleshooting
        1. 🚧 Smithery Integration 🚧 (work in progress)
          1. Integration Architecture
        2. 🤝 Contributing
          1. 📖 Learn More
            1. 📄 License

              Related MCP Servers

              • A
                security
                F
                license
                A
                quality
                Enables interaction with the Flutter SDK by providing tools to analyze and apply fixes to Dart and Flutter files.
                Last updated -
                2
                3
                JavaScript
              • A
                security
                A
                license
                A
                quality
                A Dart-based MCP server implementation that enables AI-assisted task management, document handling, and workspace organization through standardized tools and seamless Dart integration.
                Last updated -
                10
                599
                2
                JavaScript
                MIT License
                • Linux
                • Apple
              • A
                security
                A
                license
                A
                quality
                A distributable Model Context Protocol (MCP) server that exposes Dart SDK commands for AI-powered development. This server bridges the gap between AI coding assistants and Dart/Flutter development workflows by implementing the Model Context Protocol (MCP).
                Last updated -
                10
                11
                2
                TypeScript
                MIT License
                • Apple
                • Linux
              • -
                security
                F
                license
                -
                quality
                An MCP server that provides detailed information about your development environment to the Cursor code editor, enabling more context-aware assistance.
                Last updated -
                1
                Python
                • Linux
                • Apple

              View all related MCP servers

              ID: qnu3f0fa20