Flutter MCP Toolkit connects a running Flutter debug app to AI assistants through MCP, so your assistant can inspect UI, read runtime errors, hot reload, and run app-defined tools.

The toolkit gives an AI assistant a shared window and control loop into a running Flutter app, so it can stop guessing and verify changes with runtime proof.

• Flutter-specific workflows: screenshots, app errors, view details, hot reload/restart.
• Dynamic tool registry: your app can register custom tools/resources at runtime.
• Better AI debugging loops: tools return structured data and retry guidance.
• Multi-target safety: explicit connection.targetId flow when multiple debug apps are running.

Read more in Why this repo matters.

Use Feature map for a capabilities overview and where to learn each one. Need a complete page-by-page index? Docs map

Need to decide between terminal automation and AI-client tool usage? CLI vs MCP

Need ready-to-run terminal commands? CLI quick recipes

• Dynamic Tools Registration (YouTube)
• Cursor Setup Walkthrough (YouTube)
• All videos and watch order

• Who contributed and how
• How to contribute