Dart Query

io.github.standardbeaglePublished by GitHub account standardbeaglev0.3.5Updated Nov 3, 2026

Dart AI task management MCP with batch operations, DartQL selectors, CSV import, zero context rot

VerifiedSTDIODesktop onlyProductivity & WorkflowDeveloper Tools

Overview

AI-generated overview

Local MCP server for Dart AI task management, letting an assistant query, create, update and bulk-edit tasks and docs with DartQL selectors.

What you can do
  • Explore capabilities and workspace configuration
  • Create, read, update, delete tasks and add task comments
  • List and full-text search tasks with filters
  • Bulk update or delete tasks via DartQL selectors, with batch status checks
  • Import tasks in bulk from CSV with validation
  • List, create, read, update and delete documents
When to use it
Useful when you manage tasks and documents in Dart AI and want an assistant to make changes in bulk without flooding the context window with per-task JSON. Best for teams doing selector-based mass updates, CSV imports, or routine task and doc maintenance.
Requirements
Runs locally over stdio, typically via npx with the npm package. Requires a Dart AI account and an API token supplied in the DART_TOKEN environment variable. Network access to Dart AI is needed.
Before you install
All operations hit production Dart AI data with no sandbox, so writes and deletes are real. Batch deletes require an explicit confirm flag and tasks go to trash rather than being permanently removed. Use dry-run previews before batch updates and CSV imports. The DART_TOKEN credential grants access to your Dart AI workspace and should be kept out of shared configs.

Installation

In SourceWeft

  1. Open Dart Query in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

dart-query

MCP server for Dart AI task management, optimized for batch operations and minimal context usage.

Instead of looping through tasks one-by-one (filling your context window with intermediate JSON), dart-query uses DartQL selectors and server-side batch operations to update hundreds of tasks in a single call. A 50-task update that would normally consume ~30K tokens takes ~200 tokens with zero context rot.

Quick Start

1. Get Your Dart AI Token

Visit https://app.dartai.com/?settings=account and copy your token (starts with dsa_).

2. Configure MCP

npx (recommended)

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

SLOP-MCP (v0.10.0+)

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

3. Verify

info({ level: "overview" })

4. Example: Batch Update

typescript
// Preview firstbatch_update_tasks({  selector: "dartboard = 'Engineering' AND priority = 'high'",  updates: { status: "Doing" },  dry_run: true})
// Executebatch_update_tasks({  selector: "dartboard = 'Engineering' AND priority = 'high'",  updates: { status: "Doing" },  dry_run: false})

Tools

GroupToolsPurpose
Discoveryinfo, get_configExplore capabilities, workspace config
Task CRUDcreate_task, get_task, update_task, delete_task, add_task_commentSingle task operations
Querylist_tasks, search_tasksFind tasks with filters or full-text search
Batchbatch_update_tasks, batch_delete_tasks, get_batch_statusBulk operations with DartQL selectors
Importimport_tasks_csvBulk create from CSV with validation
Docslist_docs, create_doc, get_doc, update_doc, delete_docDocument management

See TOOLS.md for full parameter references, DartQL syntax, and CSV import format.

DartQL Selectors

SQL-92 WHERE clause syntax for targeting tasks in batch operations:

sql
dartboard = 'Engineering' AND priority = 'high' AND tags CONTAINS 'bug'due_at < '2026-01-18' AND status <> 'Done'title LIKE 'Task%'                          -- starts withtitle LIKE '%auth%'                         -- contains substring

Operators: =, !=, <>, >, >=, <, <=, LIKE, IN, NOT IN, BETWEEN, IS NULL, IS NOT NULL, CONTAINS Aliases: INCLUDES/HAS → CONTAINS · <> → != LIKE wildcards: % = any characters, _ = single character (case-insensitive)

Safety

All Dart AI operations are production (no sandbox). dart-query provides:

  • Dry-run mode on all batch operations — preview before executing
  • Validation phase for CSV imports — catch errors before creating anything
  • Confirmation flag (confirm: true) required for batch deletes
  • Recoverable deletes — tasks move to trash, not permanent deletion

License

MIT

Source: README.md at commit 448a152

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.3.5LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts