mcp_flutter
MCP server and MCP Toolkit for Flutter and Dart VM - supports dynamic tooling
claude mcp add --transport stdio arenukvern-mcp_flutter docker run -i arenukvern/mcp_flutter \ --env DEBUG="Enable verbose debug logs (true/false)" \ --env MCP_PORT="Port for MCP server (default depends on image, typically 8181 or 8182)"
How to use
This MCP server exposes a Flutter-based MCP Server that bridges your Flutter apps with AI coding assistants (Cursor, Claude, Cline, Windsurf, RooCode, or any MCP-enabled AI tool). It supports dynamic tools registration, so your Flutter app can register custom tools at runtime and expose them to connected agents. To start, launch the server (for example via Docker) and point your MCP clients to the server endpoint. Once running, you can use the included Flutter tools like get_app_errors, view_screenshot, and get_view_details, as well as dynamically registered tools provided by your Flutter app. Configure the server through the command line and configuration docs, then test integrations with an AI agent to verify tool discovery and response flows.
How to install
Prerequisites:
- Docker installed on your machine (recommended for quick start)
- Optional: Flutter/Dart SDK if you prefer building or running locally without Docker
Installation steps (Docker):
- Ensure Docker is running on your machine.
- Pull and run the MCP Flutter server image: docker run -i arenukvern/mcp_flutter
- If needed, map ports to your host and set environment variables (for example MCP_PORT or DEBUG) when starting the container: docker run -i -p 8181:8181 -e MCP_PORT=8181 -e DEBUG=true arenukvern/mcp_flutter
Alternative (local Dart/Flutter setup):
- Install Flutter and ensure Dart is available.
- Clone the repository: git clone https://github.com/Arenukvern/mcp_flutter.git
- Navigate to the project directory and follow the project’s QUICK_START.md and mcp_server_dart README for running the Dart-based MCP server locally.
- Start the server with the recommended dart/flutter commands as documented in the repository.
Prerequisites summary:
- Docker (recommended) or Flutter/Dart SDK
- Basic familiarity with running containers or Dart/Flutter apps
Additional notes
Tips and caveats:
- Dynamic Tools Registration lets your Flutter app publish custom tools at runtime; ensure your app initializes mcp_toolkit and registers tools via MCPToolkitBinding.instance.addEntries().
- Some RPC methods (e.g., dump_render_tree) can generate large token usage; the server may disable them by default and require a flag to enable. Check the CLI docs for enabling dumps.
- If tools do not appear in an agent, verify that the Flutter app is running in debug mode, the port matches between client and server, and that tools are properly registered in the app (listClientToolsAndResources can help).
- If you use Docker, ensure port mappings align with your agent configuration and that any required environment variables (like MCP_PORT) are set.
- This server focuses on dynamic tool registration and Flutter-based tooling; for broader MCP capabilities, refer to the Quick Start and Configuration docs in the repository.
Related MCP Servers
frontmcp
TypeScript-first framework for the Model Context Protocol (MCP). You write clean, typed code; FrontMCP handles the protocol, transport, DI, session/auth, and execution flow.
shinzo-ts
TypeScript SDK for MCP server observability, built on OpenTelemetry. Gain insight into agent usage patterns, contextualize tool calls, and analyze server performance across platforms. Integrate with any OpenTelemetry ingest service including the Shinzo platform.
n8n-workflow-builder
MCP server that allow LLM in agent mode builds n8n workflows for you
openai -agent-dotnet
Sample to create an AI Agent using OpenAI models with any MCP server running on Azure Container Apps
mcp-bun
Bun Javascript Runtime MCP Server for AI Agents
cbn_mcp
A Model Context Protocol (MCP) server for accessing Central Bank of Nigeria (CBN) data and circulars. Connect this server to Cursor, Claude Desktop, or any MCP-compatible application to access CBN regulatory information directly in your AI conversations. 🚀