Dart
Interact with task, doc, and project data in Dart, an AI-native project management tool
Dart is Project Management powered by AI.
[!WARNING] The Dart local MCP server is deprecated in favor of the simplified and improved hosted Dart MCP server, which you can configure with these instructions.
Deprecated information
`dart-mcp-server` is the official AI [Model Context Protocol (MCP)](https://github.com/modelcontextprotocol) server for Dart.Features
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)add_task_comment- Add a comment to an existing task
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.
Setup
The easiest way to run the MCP server is with npx, but a Docker setup is also available.
Find the MCP settings file for the client
Claude Desktop
- Install Claude Desktop as needed
- Open the config file by opening the Claude Desktop app, going into its Settings, opening the 'Developer' tab, and clicking the 'Edit Config' button
- Follow the 'Set up the MCP server' steps below
Claude Code
-
Install Claude Code as needed
-
Copy your authentication token from your Dart profile
-
Run the following command, being sure to replace
dsa...with your actual Dart tokenclaude mcp add dart -e DART_TOKEN=dsa_... -- npx -y dart-mcp-server@latest
Cursor
- Install Cursor as needed
- Open the config file by opening Cursor, going into 'Cursor Settings' (not the normal VSCode IDE settings), opening the 'MCP' tab, and clicking the 'Add new global MCP server' button
- Follow the 'Set up the MCP server' steps below
Cline
- Install Cline in your IDE as needed
- Open the config file by opening your IDE, opening the Cline sidebar, clicking the 'MCP Servers' icon button that is second from left at the top, opening the 'Installed' tab, and clicking the 'Configure MCP Servers' button
- Follow the 'Set up the MCP server' steps below
Windsurf
- Install Windsurf as needed
- Open the config file by opening Windsurf, going into 'Windsurf Settings' (not the normal VSCode IDE settings), opening the 'Cascade' tab, and clicking the 'View raw config' button in the 'Model Context Protocol (MCP) Servers' section
- Follow the 'Set up the MCP server' steps below
Any other client
- Find the MCP settings file, usually something like
[client]_mcp_config.json - Follow the 'Set up the MCP server' steps below
Set up the MCP server
-
Install npx, which comes bundled with Node, as needed
-
Copy your authentication token from your Dart profile
-
Add the following to your MCP setup, being sure to replace
dsa...with your actual Dart token{ "mcpServers": { "Dart": { "command": "npx", "args": ["-y", "dart-mcp-server@latest"], "env": { "DART_TOKEN": "dsa_..." } } } }
Variant: setup with Docker
If the npx setup above does not work well, we also provide a Docker setup. Follow the instructions above to find the MCP settings file
-
Install Docker as needed
-
Build the Docker container with
docker build -t mcp/dart . -
Copy your authentication token from your Dart profile
-
Add the following to your MCP setup, being sure to replace
dsa...with your actual Dart token{ "mcpServers": { "Dart": { "command": "bash", "args": [ "-c", "docker rm -f dart-mcp >/dev/null 2>&1 || true; docker run -i --rm --name dart-mcp -e DART_TOKEN mcp/dart" ], "env": { "DART_TOKEN": "dsa_..." } } } }
Help and Resources
- Homepage
- Web App
- Help Center
- Bugs and Features
- Library Source
- Chat on Discord
- Email us at [email protected]
Contributing
Contributions are welcome! Please open an issue or submit a pull request.
License
This project is licensed under the MIT License.
Máy chủ liên quan
Ads MCP
Remote MCP server for Ad campaign planning, research, and cross-platform ad creation. Supports Google Ads Search & Performance Max and TikTok at launch, with additional networks planned.
clipboard-mcp
MCP server that reads and writes the system clipboard — tables, text, code, JSON, URLs, images, and more. Preserves spreadsheet structure (rows/columns) that is lost when pasting into Claude directly. Claude can also write results back to your clipboard.
AppContext MCP
AppContext gives your AI coding agent instant visual insight into what you're developing, so it can fix issues, refine UI, and accelerate your development workflow in real time.
Gmail MCP Server
An MCP server for interacting with Gmail and Google Calendar, enabling context-aware email and event management.
roampal-core
Persistent memory for Claude Code with outcome-based learning. Tracks what helped vs failed, auto-injects context via hooks.
Zotero MCP
Connect your Zotero research library with AI assistants. Supports local/web API access, PDF annotation extraction, and advanced search.
Pulsetic MCP Server
The Pulsetic MCP Server connects Pulsetic monitoring with AI agents and MCP-compatible tools, enabling direct access to uptime data, cron monitoring results, incident management workflows, and status page information through the Model Context Protocol (MCP). It allows teams to securely expose operational monitoring data in a structured format, making it easy to build AI-driven automation, monitoring assistants, and intelligent operational workflows without custom middleware.
ChatExcel
A powerful server for Excel file processing, data analysis, and visualization, leveraging Python and Go for high performance.
PowerPoint MCP Server
Manipulate PowerPoint presentations using the python-pptx library.
sharepoint-mcp
The MCP Server that gives your AI agent a brain for Microsoft SharePoint