dart

This MCP server exposes Dart-specific capabilities to AI assistants via a standardized MCP interface. It enables task management (create/update tasks, set priorities and status, assign to team members), document management (create and organize documents or reports with markdown support), and space/workspace management (create workspaces, organize content in folders, and control access). It also integrates with Dartboard for default status handling and team collaboration. You can interact with this server using MCP tools such as create_task, update_task, get_default_status, get_dartboards, create_space, and create_doc, among others. To use it, ensure your environment variables are configured (notably your DART_TOKEN) and run the server (via npm start after installation or via your preferred runtime command). Once running, you can invoke the provided MCP tools to manage tasks, documents, spaces, and workflows within your Dart-enabled environment.

Typical workflows include creating a new task with create_task, updating its status with update_task, creating folders or spaces with create_space or create_folder, and generating documents or reports with create_doc. The server is designed to be consumed by AI assistants, enabling scripted, transactional changes to Dart projects and workspaces through standardized MCP tool invocations.

Prerequisites:

• Node.js 16.x or higher
• Python 3.8 or higher
• Dart Python SDK installed (pip install dart-sdk)
• A valid Dart API token

Option A: Installing via Smithery (recommended for Claude/Desktop integration)

npx -y @smithery/cli install @jmanhype/dart-mcp-server --client claude

Option B: Manual installation

1. Clone the repository:

git clone https://github.com/jmanhype/dart-mcp-server.git
cd dart-mcp-server

2. Install Node.js dependencies:

npm install

3. Set up Python environment and install Dart SDK:

# Create and activate virtual environment
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install Dart SDK
pip install dart-sdk

4. Set up environment variables:

# Copy example environment file
cp .env.example .env

# Edit .env with your configuration
# Required: DART_TOKEN
# Optional: PYTHONPATH (path to dart sdk)

Environment variables to configure (example):

DART_TOKEN=your_dart_token_here
# Optional: Path to your Dart SDK installation
PYTHONPATH=/path/to/dart/sdk
# Optional: Python executable path (defaults to system Python)
PYTHON_PATH=/path/to/python

5. Start the MCP server (after building if applicable):

# Build TypeScript if required by the project
npm run build

# Start the MCP server
npm start

Notes and tips:

• The server relies on your Dart API token, exposed via DART_TOKEN. Keep this token secure and do not commit it.
• If you encounter Python import errors for dart-sdk, ensure PYTHONPATH points to your Dart SDK installation or its Python bindings.
• When using Smithery-based installation, the server is often provided as a CLI integration with Claude; ensure your client configuration matches your AI assistant.
• Common issues include mismatched Node/Python versions or missing environment variables. Double-check DART_TOKEN and PYTHONPATH if the server fails to initialize.
• For MCP operations, you’ll typically call tools like create_task, update_task, create_doc, create_space, get_dartboards, and get_default_status to manage your workflow programmatically.