The MCP or Model Context Protocol is an open protocol built by Anthropic that provides a standard on how applications provide context to LLMs. It's primary use today is in linking with Anthropic's AI Claude, although other apps also use the protocol.
Dart's MCP server is hosted here on github at the following URL: https://github.com/its-dart/dart-mcp-server. The easiest way to run the MCP server is with npx, although a Docker setup is also available.
To set up the integration with Claude see our dedicated article. Otherwise read on to learn more about our MCP's capabilities:
Prompts
The following prompts are available
create-task
- Create a new task in Dart with title, description, status, priority, and assigneecreate-doc
- Create a new document in Dart with title, text content, and foldersummarize-tasks
- Get a summary of tasks with optional filtering by status and assignee
These prompts make it easy for AI assistants to perform common actions in Dart without needing to understand the underlying API details.
Resource templates
The following resources are available
dart-config:
- Configuration information about the user's spacedart-task:///{taskId}
- Detailed information about specific tasksdart-doc:///{docId}
- Detailed information about specific docs
Tools
The following tools are available
Task management
get_config
- Get information about the user's space, including available assignees, dartboards, folders, statuses, tags, priorities, and sizeslist_tasks
- List tasks with optional filtering by assignee, status, dartboard, priority, due date, and morecreate_task
- Create a new task with title, description, status, priority, size, dates, dartboard, assignees, tags, and parent taskget_task
- Retrieve an existing task by its IDupdate_task
- Update an existing task's propertiesdelete_task
- Move a task to the trash (recoverable)
Document management
list_docs
- List docs with optional filtering by folder, title, text content, and morecreate_doc
- Create a new doc with title, text content, and folderget_doc
- Retrieve an existing doc by its IDupdate_doc
- Update an existing doc's propertiesdelete_doc
- Move a doc to the trash (recoverable)
Each tool supports comprehensive input validation and returns structured JSON responses.