mcp_flutter MCP — Casos de uso, Instalar & Demo en vivo

Por qué usarlo

Características clave

get_app_errors — condensed error info from the running app
view_screenshot — real screenshots (enable with --images)
get_view_details — screen size, pixel ratio, widget info
Dynamic tool registration — your app registers bespoke tools at runtime
Works with Cursor, Claude (Desktop/Code), Cline, Windsurf via stdio

Demo en vivo

Cómo se ve en la práctica

flutter.replay ▶ listo

0/0

Instalar

Elige tu cliente

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "flutter": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/Arenukvern/mcp_flutter"
      ],
      "_inferred": true
    }
  }
}

Abre Claude Desktop → Settings → Developer → Edit Config. Reinicia después de guardar.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "flutter": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/Arenukvern/mcp_flutter"
      ],
      "_inferred": true
    }
  }
}

Cursor usa el mismo esquema mcpServers que Claude Desktop. La configuración del proyecto prevalece sobre la global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "flutter": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/Arenukvern/mcp_flutter"
      ],
      "_inferred": true
    }
  }
}

Haz clic en el icono MCP Servers de la barra lateral de Cline y luego en "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "flutter": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/Arenukvern/mcp_flutter"
      ],
      "_inferred": true
    }
  }
}

Mismo formato que Claude Desktop. Reinicia Windsurf para aplicar.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "flutter",
      "command": "TODO",
      "args": [
        "See README: https://github.com/Arenukvern/mcp_flutter"
      ]
    }
  ]
}

Continue usa un array de objetos de servidor en lugar de un mapa.

~/.config/zed/settings.json

{
  "context_servers": {
    "flutter": {
      "command": {
        "path": "TODO",
        "args": [
          "See README: https://github.com/Arenukvern/mcp_flutter"
        ]
      }
    }
  }
}

Añádelo a context_servers. Zed recarga en caliente al guardar.

claude mcp add flutter -- TODO 'See README: https://github.com/Arenukvern/mcp_flutter'

Un solo comando. Verifica con claude mcp list. Quita con claude mcp remove.

Casos de uso

Usos del mundo real: mcp_flutter

Debug a Flutter render error with AI eyes on the running app

👤 Flutter devs ⏱ ~15 min intermediate

Cuándo usarlo: You're iterating on UI and something broke. Instead of describing it, let the AI see the screenshot + errors.

Requisitos previos

Flutter app with mcp_toolkit package — Add to pubspec.yaml and initialize in main()
Running in debug mode — flutter run — the server connects to Dart VM service

Flujo

Connect

Connect to my running Flutter app (VM port 8181) via mcp_flutter.✓ Copiado

→ Tools list now includes get_app_errors, view_screenshot
Capture state

Take a screenshot of the current view. Also pull any errors from the last 60 seconds.✓ Copiado

→ Screenshot + error log
Suggest fix

Based on this error and screenshot, what's wrong and how do I fix it?✓ Copiado

→ Code diff proposal

Resultado: Tight debug loop where the AI can verify each fix by looking at the next screenshot.

Errores comunes

Screenshot tool disabled by default — Start the server with --images flag
VM port conflicts when running multiple apps — Specify --vm-service-port per app; default 8181

Expose your app's test harness as MCP tools

👤 Flutter devs building QA workflows ⏱ ~30 min intermediate

Cuándo usarlo: Your app has debug-only seeders / state toggles you want AI to call during dev.

Flujo

Register tools in Dart

Using mcp_toolkit, register tools seed_users(count: int) and set_feature_flag(name: str, value: bool) in my app's debug initializer.✓ Copiado

→ Dart snippet registering tools
Drive from Claude

Seed 10 users, flip feature flag 'new_checkout' to true, take screenshot of checkout screen.✓ Copiado

→ Multi-step tool call sequence with final screenshot

Resultado: Faster manual QA via chat-driven state manipulation.

Errores comunes

Tools shipped to release mode accidentally — Gate registration with kDebugMode — release builds don't see them

Understand a confusing widget tree

👤 Flutter devs inheriting someone else's code ⏱ ~20 min intermediate

Cuándo usarlo: You're trying to understand why a screen renders a certain way and the code has 8 levels of nested Builders.

Flujo

Get view details

get_view_details for the current screen and summarize the widget hierarchy.✓ Copiado

→ Widget tree summary
Ask why

Why does this text overflow? Reference specific widgets in the tree.✓ Copiado

→ Layout reasoning grounded in actual tree

Resultado: Faster onboarding to unfamiliar Flutter code.

Errores comunes

Big widget trees blow up token budget — Ask for a depth-limited summary first, then drill in

Combinaciones

Combínalo con otros MCPs para multiplicar por 10

flutter + git-2

Debug → fix → commit loop

Screenshot, diagnose, have me apply the fix, then git_commit with message describing the fix.✓ Copiado

Herramientas

Lo que expone este MCP

Herramienta	Entradas	Cuándo llamar	Coste
get_app_errors	since?: int (seconds)	After triggering a bug in the running app	free
view_screenshot		Visual verification; requires --images flag	tokens per image
get_view_details		Understand layout / screen geometry	free
<custom>	Varies per app registration	Whatever you register via mcp_toolkit	free

Coste y límites

Lo que cuesta ejecutarlo

Cuota de API: None
Tokens por llamada: Screenshots are large (~1-3k vision tokens); widget trees 500-5k
Monetario: Free, MIT
Consejo: Disable screenshots (remove --images) when debugging non-visual issues — widget tree + errors are much cheaper.

Seguridad

Permisos, secretos, alcance

Almacenamiento de credenciales: None — connects to local Dart VM service

Salida de datos: Local only in typical use; screenshots go to your LLM provider

No conceder nunca: Expose VM service port to the network in release builds

Only works in debug/profile mode — release builds lock down the VM service.
Tested on macOS/iOS; Android and desktop support is marked 'not tested' in the README.

Resolución de problemas

Errores comunes y soluciones

Cannot connect to Dart VM

Start your Flutter app first, then the MCP server. Confirm VM port (usually 8181) matches config.

Verificar: curl http://127.0.0.1:8181/

Screenshots return 404

Server started without --images flag. Restart with the flag.

Custom tools not showing up

mcp_toolkit must be initialized after runApp; verify kDebugMode gate isn't false in your build.

Alternativas

mcp_flutter vs otros

Alternativa	Cuándo usarla	Contrapartida
Flutter DevTools MCP	You want the official Flutter tooling	Doesn't exist yet as an MCP; this is the closest

Más

Recursos

📖 Lee el README oficial en GitHub

🐙 Ver issues abiertas

🔍 Ver todos los 400+ servidores MCP y Skills