dart-connect-dart-tooling-daemon

To connect to the Dart Tooling Daemon for editor/runtime data, connect using a user-provided DTD URI before using related Dart tools.

⭐6stars🔀3forks📁View on GitHub🕐Updated Jan 7, 2026

When & Why to Use This Skill

This Claude skill enables seamless integration with the Dart Tooling Daemon (DTD), allowing AI agents to access critical editor and runtime data. By establishing a connection via a user-provided DTD URI, it empowers the agent to interact with the Dart ecosystem, facilitating advanced debugging, real-time code analysis, and environment synchronization for Flutter and Dart developers.

Use Cases

  • Real-time Debugging: Connect to the Dart Tooling Daemon to fetch live runtime data and inspect the state of a running Dart or Flutter application.
  • IDE Context Synchronization: Bridge the gap between the AI agent and the local development environment by sharing editor data and metadata for more accurate code assistance.
  • Automated Tooling Integration: Enable AI-driven workflows that require interaction with Dart's internal tooling services for performance monitoring or static analysis.
namedart-connect-dart-tooling-daemon
description"To connect to the Dart Tooling Daemon for editor/runtime data, connect using a user-provided DTD URI before using related Dart tools."

Usage

Use the MCP tool dev-swarm.request to send the payload as a JSON string:

{"server_id":"dart","tool_name":"connect_dart_tooling_daemon","arguments":{}}

Tool Description

Connects to the Dart Tooling Daemon. You should get the uri either from available tools or the user, do not just make up a random URI to pass. When asking the user for the uri, you should suggest the "Copy DTD Uri to clipboard" action. When reconnecting after losing a connection, always request a new uri first.

Arguments Schema

The schema below describes the arguments object in the request payload.

{
  "type": "object",
  "properties": {
    "uri": {
      "type": "string"
    }
  },
  "required": [
    "uri"
  ]
}

Background Tasks

If the tool returns a task id, poll the task status via the MCP request tool:

{"server_id":"dart","method":"tasks/status","params":{"task_id":"<task_id>"}}