Integration

Dart integration

Dart is a project management workspace for teams and AI agents. Create, read, update, move and trash tasks, list them with filters on dartboard, status, assignee, tags, priority and dates, comment on them, attach files from a URL and log time; create, edit and trash docs; read dartboards, folders, views and the workspace configuration (statuses, tags, priorities, sizes, task types); manage the workspace's AI agents and skills, and webhooks that report workspace events. The login-token exchange and the help center search are not exposed. Authentication is a Dart API token from the account settings, sent as a Bearer token.

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Dart.Built from the 38 Dart tools below, on the connection you add once.

What you can do with Dart

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

List, 6 operations

  • list_agentsList agentsGETList all agents in the workspace. Agents are AI assistants that can be assigned tasks and have customizable instructions.
  • list_commentsList commentsGETList comments for a task with filtering options. Filter by author, text content, or date range. Sort by date or hierarchical thread order. Task ID required. Supports pagination.
  • list_docsList docsGETList docs with filtering and search capabilities. Filter by folder, title, text content, or use full-text search. Sort by creation/update date or title. Supports pagination.
  • list_skillsList skillsGETList all skills in the workspace. Skills are user-defined instructions or templates for performing specific task types.
  • list_tasksList tasksGETList tasks with powerful filtering options. Filter by dartboard, status, assignee, tags, priority, dates, completion state, view, and more. Supports pagination with limit/offset.
  • list_webhooksList webhooksGETList all webhooks in the workspace.

Agent, 4 operations

  • create_agentCreate agentPOSTCreate a new agent in the workspace with a name and optional description or instructions.
  • delete_agentDelete agentDELETEDelete an agent by its ID.
  • get_agentGet agentGETRetrieve an existing agent by its ID, including its name and current description or instructions.
  • update_agentUpdate agentPUTUpdate an existing agent. The agent ID and fields to change. Use the same ID as the path id; omitted top-level fields keep their current values.

Doc, 4 operations

  • create_docCreate docPOSTRecord a new doc that the user intends to write down. This will save the doc in Dart for later access, search, etc. By default the created doc will be in the Docs folder. More information can be included in the text.
  • delete_docDelete docDELETEMove an existing doc to the trash, where it can be recovered if needed. Nothing else about the doc will be changed.
  • get_docGet docGETRetrieve an existing doc. This will return the doc's information, including the title, folder, text and others.
  • update_docUpdate docPUTUpdate certain properties of an existing doc. This will save the doc in Dart for later access, search, etc. Any properties that are not specified will not be changed.

Skill, 4 operations

  • create_skillCreate skillPOSTCreate a new custom skill with a title and instructions in markdown. The skill will be available to all workspace members.
  • delete_skillDelete skillDELETEDelete a skill by its ID. The skill will be permanently removed from the workspace.
  • get_skillGet skillGETRetrieve an existing skill by its ID. Returns the skill's title and instructions.
  • update_skillUpdate skillPUTUpdate an existing skill's title and/or instructions. Only the fields provided will be updated. The skill is identified by its ID in the URL.

Task, 4 operations

  • create_taskCreate taskPOSTRecord a new task that the user intends to do. By default the task will be assigned to the current user, have an unstarted status, have no parent, and be in the default dartboard. More information can be included in the description.
  • delete_taskDelete taskDELETEMove an existing task to the trash, where it can be recovered if needed. Nothing else about the task will be changed.
  • get_taskGet taskGETRetrieve an existing task. This will return the task's information, including the title, dartboard, status, description and others.
  • update_taskUpdate taskPUTUpdate properties of an existing task. For customProperties, use property NAME (not ID) as key. Get property names from workspace config. Example: {"customTextProperty": "Some text"}. Fields not provided are unchanged.

Webhook, 4 operations

  • create_webhookCreate webhookPOSTCreate a new webhook that sends selected workspace events to a URL.
  • delete_webhookDelete webhookDELETEDelete a webhook by its ID.
  • get_webhookGet webhookGETRetrieve an existing webhook by its ID.
  • update_webhookUpdate webhookPUTUpdate an existing webhook. Only the fields provided will be updated.

By title, 1 operation

  • retrieve_skill_by_titleRetrieve skill by titleGETRetrieve a skill by its title. Skills are user-defined instructions or templates for performing specific task types in the workspace. Returns the skill's title and instructions if found.

Comment, 1 operation

  • add_task_commentAdd task commentPOSTRecord a new comment that the user intends to add to a given task. This will save the comment in Dart for later access, search, etc.

Config, 1 operation

  • get_configGet configGETGet information about the user's space, including all of the possible values that can be provided to other endpoints.

Dartboard, 1 operation

  • get_dartboardGet dartboardGETRetrieve an existing dartboard. This will return the dartboard's information, including the title and description.

Folder, 1 operation

  • get_folderGet folderGETRetrieve an existing folder. This will return the folder's information, including the title, description, all docs within it, and others.

From url, 1 operation

  • add_task_attachment_from_urlAdd task attachment from urlPOSTAttach a file from a provided URL to a task. The file will be downloaded and attached asynchronously. This operation may take a few moments to complete.

Me, 1 operation

  • get_meGet meGETCheck the current public API authentication token and return the authenticated user.

Move, 1 operation

  • move_taskMove taskPOSTMove a task to a specific position within results sorted by the order field. Use afterTaskId to place the task after a specific task, or beforeTaskId to place it before one.

Time tracking, 1 operation

  • add_task_time_trackingAdd task time trackingPOSTRecord an additional time tracking entry on a task and return the updated task with refreshed time tracking.

Update description, 1 operation

  • update_task_descriptionUpdate task descriptionPOSTApply targeted text updates to a task's description; use instead of update_task when only the description changes.

Update text, 1 operation

  • update_doc_textUpdate doc textPOSTApply targeted text updates to a doc's content; use instead of update_doc when only the text body changes.

View, 1 operation

  • get_viewGet viewGETRetrieve an existing view. This will return the view's information, including the title, description, and others.

Use Dart from Claude Code, Cursor or Codex

Connect Dart in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Dart operations become tools the client can call, next to every other integration you connected.

Claude Code
claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"
Codex (~/.codex/config.toml)
[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"
Cursor, Claude Desktop and other JSON configs
{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Dart

  1. Create your workspace

    Sign up free. Nothing to install.

  2. Connect Dart once

    Add your Dart connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.

  3. Describe the job in chat

    The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Dart integration FAQ

What can you do with the Dart integration?

LiveContext exposes 38 operations on Dart, covering list, agent, doc and skill.

Popular integrations

Browse the whole catalog