Skip to content
dart-query

Installation and Setup

Prerequisites

Section titled “Prerequisites”
  • Node.js 18+ (for npx or global install)
  • A Dart AI account at dartai.com
  • An MCP-compatible client (Claude Desktop, Claude Code, Cursor, or any MCP host)

Step 1: Get Your Dart AI Token

Section titled “Step 1: Get Your Dart AI Token”
  1. Go to Dart AI Settings
  2. Copy your API token (starts with dsa_)
  3. Keep it handy for the next step

Step 2: Install dart-query

Section titled “Step 2: Install dart-query”

Choose one of three methods depending on your setup.

Section titled “Option A: npx (Recommended)”

No global install needed. Add this to your MCP client configuration:

{
  "mcpServers": {
    "dart-query": {
      "command": "npx",
      "args": ["-y", "@standardbeagle/dart-query"],
      "env": {
        "DART_TOKEN": "dsa_your_token_here"
      }
    }
  }
}

Where to put this file:

  • Claude Desktop: ~/.config/claude/claude_desktop_config.json (Linux/Mac) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
  • Claude Code: ~/.claude/mcp.json or project-level .mcp.json
  • Cursor: Settings > MCP Servers

Option B: Global npm Install

Section titled “Option B: Global npm Install”
Terminal window
npm install -g @standardbeagle/dart-query

Then configure your MCP client to use the dart-query command directly:

{
  "mcpServers": {
    "dart-query": {
      "command": "dart-query",
      "env": {
        "DART_TOKEN": "dsa_your_token_here"
      }
    }
  }
}

Option C: SLOP-MCP Registration

Section titled “Option C: SLOP-MCP Registration”

If you use slop-mcp to manage your MCP servers:

Terminal window
slop register dart-query \
  --command npx \
  --args "-y" "@standardbeagle/dart-query" \
  --env DART_TOKEN=dsa_your_token_here \
  --scope user

Step 3: Verify the Connection

Section titled “Step 3: Verify the Connection”

After configuring your MCP client, restart it and run:

info({ level: "overview" })

You should see a summary of your Dart AI workspace including available dartboards, statuses, and tool categories.

Step 4: Run Your First Batch Operation

Section titled “Step 4: Run Your First Batch Operation”

Try a dry-run batch update to see dart-query in action without changing anything:

// Preview: find and start all high-priority tasks on a dartboard
execute_dartql({
  query: "UPDATE WHERE dartboard = 'My Project' AND priority = 4 SET status = 'Doing'",
  dry_run: true
})

The response shows exactly which tasks would be affected and what would change. When you are ready, set dry_run: false to execute.

Environment Variable Reference

Section titled “Environment Variable Reference”
VariableRequiredDescription
DART_TOKENYesYour Dart AI API token (starts with dsa_)

Next Steps

Section titled “Next Steps”