Flutter Mcp Toolkit
Inspect and drive Flutter debug apps/games: semantic snapshots, search, and custom client tools
The toolkit connects a running Flutter debug app to AI assistants through MCP. AI assistants can inspect UI, read runtime errors, hot reload, and run app-defined tools. It provides a shared window and control loop for AI assistants into a running Flutter app.
It includes a dynamic tool registry allowing apps to register custom tools/resources at runtime. It supports multi-target safety with explicit connection.targetId flow for multiple debug apps. The toolkit has features for Flutter-specific workflows like screenshots, app errors, view details, hot reload/restart.
Tools return structured data and retry guidance for better AI debugging loops.
Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.