Goodday MCP Server

Integrate with the Goodday project management platform to manage projects, tasks, and users via its API.

A Model Context Protocol (MCP) server for integrating with Goodday project management platform. This server provides tools for managing projects, tasks, and users through the Goodday API v2.

- get_projects: Retrieve list of projects (with options for archived and root-only filtering)
- get_project: Get detailed information about a specific project
- create_project: Create new projects with customizable templates and settings
- get_project_users: Get users associated with a specific project

- get_project_tasks: Retrieve tasks from specific projects (with options for closed tasks and subfolders)
- get_user_assigned_tasks: Get tasks assigned to a specific user
- get_user_action_required_tasks: Get action-required tasks for a user
- get_task: Get detailed information about a specific task
- get_task_details: Get comprehensive task details including subtasks, custom fields, and full metadata
- get_task_messages: Retrieve all messages/comments for a specific task
- create_task: Create new tasks with full customization (subtasks, assignments, dates, priorities)
- update_task_status: Update task status with optional comments
- add_task_comment: Add comments to tasks

- get_goodday_sprint_tasks: Get tasks from specific sprints by project name and sprint name/number
- get_goodday_sprint_summary: Generate comprehensive sprint summaries with task details, status distribution, and key metrics

- get_users: Retrieve list of organization users
- get_user: Get detailed information about a specific user

- get_goodday_smart_query: Natural language interface for common project management queries
- search_goodday_tasks: Semantic search across tasks using VectorDB backend
- search_project_documents: Search for documents within specific projects
- get_document_content: Retrieve full content of specific documents

This package also includes an OpenWebUI tool that provides a complete interface for Goodday project management directly in chat interfaces. The OpenWebUI tool includes:

- Project Management: Get projects, project tasks, and project details
- Sprint Management: Get tasks from specific sprints by name/number, comprehensive sprint summaries
- User Management: Get tasks assigned to specific users, user details
- Task Details: Get comprehensive task information including subtasks, custom fields, and metadata
- Task Messages: Retrieve all messages and comments for tasks
- Smart Query: Natural language interface for common project management requests
- Semantic Search: Search across tasks using VectorDB backend with embeddings
- Document Management: Search project documents and retrieve document content
- Advanced Filtering: Support for archived projects, closed tasks, subfolders, and more
- Copyopenwebui/goodday_openwebui_complete_tool.pyto your OpenWebUI tools directory
- Configure the valves with your API credentials:

- api_key: Your Goodday API token
- search_url: Your VectorDB search endpoint (optional)
- bearer_token: Bearer token for search API (optional)

For semantic search functionality, you can set up a vector database using the provided n8n workflow (openwebui/n8n-workflow-goodday-vectordb.json). This workflow:

- Fetches all Goodday projects and tasks
- Extracts task messages and content
- Creates embeddings using Ollama
- Stores in Qdrant vector database
- Provides search API endpoint

Seeopenwebui/OPENWEBUI_TOOL_README.mdfor detailed usage instructions.

- Python 3.10 or higher
- UV package manager (recommended) or pip
- Goodday API token

curl -LsSf https://astral.sh/uv/install.sh | sh

git clone https://github.com/cdmx1/goodday-mcp.git cd goodday-mcp # Create virtual environment and install dependencies uv venv source .venv/bin/activate # On Windows: .venv\Scripts\activate uv sync

git clone https://github.com/cdmx1/goodday-mcp.git cd goodday-mcp pip install -e .

-

Set up environment variables: Create a.envfile in your project root or export the variable:

export GOODDAY_API_TOKEN=your_goodday_api_token_here

- Go to your Goodday organization
- Navigate to Settings → API
- Click the generate button to create a new token
-

Configure Claude Desktopby editing your configuration file:

- macOS:~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:%APPDATA%\Claude\claude_desktop_config.json

{ "mcpServers": { "goodday": { "command": "goodday-mcp", "env": { "GOODDAY_API_TOKEN": "your_goodday_api_token_here" } } } }

{ "mcpServers": { "goodday": { "command": "uv", "args": ["run", "goodday-mcp"], "env": { "GOODDAY_API_TOKEN": "your_goodday_api_token_here" } } } }

Restart Claude Desktopto load the new server.

The server communicates via stdio transport and can be integrated with any MCP-compatible client. Refer to theMCP documentationfor client-specific integration instructions.

# Get all active projects get_projects() # Get archived projects get_projects(archived=True) # Get only root-level projects get_projects(root_only=True)

create_task( project_id="project_123", title="Implement new feature", from_user_id="user_456", message="Detailed description of the task", to_user_id="user_789", deadline="2025-06-30", priority=5 )

update_task_status( task_id="task_123", user_id="user_456", status_id="status_completed", message="Task completed successfully" )

goodday-mcp/ ├── goodday_mcp/ # Main package directory │ ├── __init__.py # Package initialization │ └── main.py # Main MCP server implementation ├── pyproject.toml # Project configuration and dependencies ├── README.md # This file ├── LICENSE # MIT license ├── uv.lock # Dependency lock file └── .env # Environment variables (create this)

@mcp.tool() async def your_new_tool(param1: str, param2: Optional[int] = None) -> str: """Description of what the tool does. Args: param1: Description of parameter 1 param2: Description of optional parameter 2 """ # Implementation here return "Result"

Test the toolby running the server and testing with an MCP client.

# If installed from PyPI goodday-mcp # If running from source uv run goodday-mcp

The server will start and wait for MCP protocol messages via stdin/stdout.
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request

This project is licensed under the MIT License - see the LICENSE file for details.

- MCP Server: Create an issue in this repository
- Goodday API: Refer toGoodday API documentation
- MCP Protocol: Refer toMCP documentation

Interact with task, doc, and project data in Dart, an AI-native project management tool