Goodday MCP Server

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.

Features

Project Management

- 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

Task Management

- 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 - 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

User Management

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

OpenWebUI Integration

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

Features

- Project Management: Get projects and project tasks - Sprint Management: Get tasks from specific sprints by name/number - User Management: Get tasks assigned to specific users - Smart Query: Natural language interface for common requests - Search: Semantic search across tasks using VectorDB backend - Task Details: Get detailed task information and messages

Setup

1. Copy openwebui/goodday_openwebui_complete_tool.py to your OpenWebUI tools directory 2. 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)

Vector Database Setup (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

See openwebui/OPENWEBUI_TOOL_README.md for detailed usage instructions.

Installation

From PyPI (Recommended)

pip install goodday-mcp

From Source

Prerequisites

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

Setup with UV

1. Install UV (if not already installed):

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

   

2. Clone and set up the project:

   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

   

Setup with pip

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

Configuration

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

   export GOODDAY_API_TOKEN=your_goodday_api_token_here

   

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

Usage

Running the Server Standalone

If installed from PyPI:

goodday-mcp

If running from source with UV:

uv run goodday-mcp

Using with Claude Desktop

1. Configure Claude Desktop by editing your configuration file:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json

2. Add the server configuration:

Option A: If installed from PyPI:

   {

     "mcpServers": {

       "goodday": {

         "command": "goodday-mcp",

         "env": {

           "GOODDAY_API_TOKEN": "your_goodday_api_token_here"

         }

       }

     }

   }

   

Option B: If running from source:

   {

     "mcpServers": {

       "goodday": {

         "command": "uv",

         "args": ["run", "goodday-mcp"],

         "env": {

           "GOODDAY_API_TOKEN": "your_goodday_api_token_here"

         }

       }

     }

   }

   

3. Restart Claude Desktop to load the new server.

Using with Other MCP Clients

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

API Reference

Environment Variables

| Variable | Description | Required |
|----------|-------------|----------|
| GOODDAY_API_TOKEN | Your Goodday API token | Yes |

Tool Examples

Get Projects

```python