by urbanogardun
things3-mcp is an MCP (Model Context Protocol) server that provides comprehensive integration with Things3 on macOS, enabling AI assistants and other MCP clients to interact with Things3 for complete task management.
things3-mcp is a Model Context Protocol (MCP) server designed to bridge the gap between AI assistants and the Things3 task management application on macOS. It provides a robust set of 25 specialized tools that allow AI and other MCP clients to seamlessly interact with Things3, offering extensive capabilities for managing tasks, projects, and tags.
Things3-mcp can be used in several ways, primarily by configuring it within an MCP client like Claude Desktop. You can use npx for a quick start without installation, or install it globally via npm. For update operations, you'll need to set your Things3 authorization token as an environment variable. The server exposes various tools that can be invoked by your MCP client to perform actions within Things3.
An MCP (Model Context Protocol) server that provides comprehensive integration with Things3 on macOS. This server enables AI assistants and other MCP clients to interact with Things3 through 25 specialized tools, offering complete task management capabilities with intelligent error correction and automatic tag creation.
You can use the server without any installation:
{
"mcpServers": {
"things3": {
"command": "npx",
"args": ["things3-mcp@latest"],
"env": {
"THINGS3_AUTH_TOKEN": "your_auth_token_here"
}
}
}
}
npm install -g things3-mcp
Then add to your MCP client configuration:
{
"mcpServers": {
"things3": {
"command": "things3-mcp",
"env": {
"THINGS3_AUTH_TOKEN": "your_auth_token_here"
}
}
}
}
# Clone the repository
git clone https://github.com/urbanogardun/things3-mcp.git
cd things3-mcp
# Install dependencies
npm install
# Build the project
npm run build
For update operations (modify, complete, delete), you need to set your Things3 authorization token:
export THINGS3_AUTH_TOKEN="your_auth_token_here"
To find your authorization token:
You can also create a .env file (see .env.example).
Open Claude Desktop configuration:
~/Library/Application Support/Claude/claude_desktop_config.jsonAdd the Things3 MCP server using one of these methods:
Method 1: Using npx (easiest, no installation required)
{
"mcpServers": {
"things3": {
"command": "npx",
"args": ["things3-mcp@latest"],
"env": {
"THINGS3_AUTH_TOKEN": "your_auth_token_here"
}
}
}
}
Method 2: Global npm install
{
"mcpServers": {
"things3": {
"command": "things3-mcp",
"env": {
"THINGS3_AUTH_TOKEN": "your_auth_token_here"
}
}
}
Method 3: Local installation
{
"mcpServers": {
"things3": {
"command": "node",
"args": ["/absolute/path/to/things3-mcp/dist/index.js"]
}
}
}
Restart Claude Desktop
Use any of the methods above, adapting the configuration to your MCP client's format.
todos_listList TODOs with flexible filtering options.
Parameters:
filter: "inbox" | "today" | "upcoming" | "anytime" | "someday" | "logbook" (optional)searchText: Search within titles and notes (optional)Example:
{
"filter": "today",
"searchText": "meeting"
}
todos_getGet detailed information about a specific TODO.
Parameters:
id: The TODO's unique identifier (required)todos_createCreate a new TODO with full property support (automatically creates tags if they don't exist).
Parameters:
title: Task title (required)notes: Additional notes (optional)whenDate: ISO 8601 date string for scheduling (optional)deadline: ISO 8601 date string for due date (optional)tags: Array of tag names (optional)checklistItems: Array of checklist item titles (optional) *projectId: Assign to project (optional)areaId: Assign to area (optional)heading: Title of heading within project to add to (optional)Example:
{
"title": "Review Q4 Report",
"notes": "Focus on revenue metrics",
"whenDate": "2024-12-15T09:00:00Z",
"deadline": "2024-12-20T17:00:00Z",
"tags": ["work", "urgent"],
"checklistItems": ["Review revenue", "Check expenses", "Update forecast"],
"projectId": "project-id-here"
}
* Note on Checklists: When checklistItems are provided, the TODO is created using Things3's URL scheme instead of AppleScript. This approach has some limitations:
todos_updateUpdate an existing TODO's properties (automatically creates tags if they don't exist).
Parameters:
id: TODO identifier (required)todos_create (optional)todos_completeMark one or more TODOs as complete.
Parameters:
ids: Single ID or array of IDs (required)todos_uncompleteMark one or more TODOs as incomplete.
Parameters:
ids: Single ID or array of IDs (required)todos_deleteDelete one or more TODOs permanently.
Parameters:
ids: Single ID or array of IDs (required)projects_listList projects with optional filtering.
Parameters:
areaId: Filter by area (optional)includeCompleted: Include completed projects (optional, default: false)projects_getGet detailed project information.
Parameters:
id: Project identifier (required)projects_createCreate a new project (automatically creates tags if they don't exist).
Parameters:
name: Project name (required)notes: Project description (optional)areaId: Assign to area (optional)whenDate: Start date (optional)deadline: Due date (optional)tags: Array of tag names (optional)headings: Array of section headings (optional)projects_updateUpdate project properties (automatically creates tags if they don't exist).
Parameters:
id: Project identifier (required)projects_create except headings (optional)projects_completeMark a project as complete.
Parameters:
id: Project identifier (required)projects_deleteDelete projects completely from Things3.
Parameters:
ids: Single project ID or array of project IDs (required)areas_listList all areas.
Parameters:
includeHidden: Include hidden areas (optional, default: false)areas_createCreate a new area.
Parameters:
name: Area name (required)areas_deleteDelete areas completely from Things3.
Parameters:
ids: Single area ID or array of area IDs (required)tags_listList all tags with hierarchy information.
Returns: Array of tags with parentTagId for nested tags
tags_createCreate a new tag.
Parameters:
name: Tag name (required)parentTagId: Parent tag for nesting (optional)tags_addAdd tags to items (automatically creates tags if they don't exist).
Parameters:
itemIds: Single ID or array of TODO/Project IDs (required)tags: Array of tag names to add (required)tags_removeRemove tags from items.
Parameters:
itemIds: Single ID or array of TODO/Project IDs (required)tags: Array of tag names to remove (required)tags_deleteDelete tags completely from Things3.
Parameters:
names: Single tag name or array of tag names (required)bulk_moveMove multiple TODOs to a project or area.
Parameters:
todoIds: Array of TODO IDs (required)projectId: Target project (optional)areaId: Target area (optional)bulk_updateDatesUpdate dates for multiple TODOs.
Parameters:
todoIds: Array of TODO IDs (required)whenDate: New scheduled date or null to clear (optional)deadline: New deadline or null to clear (optional)logbook_searchSearch completed items in the logbook.
Parameters:
searchText: Search in titles and notes (optional)fromDate: Start date for range (optional)toDate: End date for range (optional)limit: Maximum results (optional, default: 50)system_launchEnsure Things3 is running and ready.
The server automatically corrects common issues:
Human: Create a new project for the website redesign with tasks for planning, design, and implementation
Claude: I'll create a website redesign project with those tasks for you.
[Creates project and tasks using the Things3 MCP tools]
Create a TODO:
{
"tool": "todos_create",
"parameters": {
"title": "Prepare presentation",
"notes": "Include Q4 metrics and projections",
"whenDate": "2024-12-10T14:00:00Z",
"tags": ["work", "presentation"]
}
}
List today's tasks:
{
"tool": "todos_list",
"parameters": {
"filter": "today"
}
}
# Install dependencies
npm install
# Run in development mode with watch
npm run dev
# Run tests
npm test
# Run integration tests (requires Things3)
npm run test:integration
# Lint code
npm run lint
# Type check
npm run type-check
things3-mcp/
├── src/
│ ├── index.ts # Entry point
│ ├── server.ts # MCP server implementation
│ ├── config.ts # Configuration management
│ ├── tools/ # Tool implementations
│ │ ├── todos.ts # TODO operations
│ │ ├── projects.ts # Project operations
│ │ ├── areas.ts # Area operations
│ │ ├── tags.ts # Tag operations
│ │ ├── bulk.ts # Bulk operations
│ │ ├── logbook.ts # Logbook search
│ │ └── system.ts # System utilities
│ ├── templates/ # AppleScript templates
│ ├── utils/ # Utility functions
│ │ ├── applescript.ts # AppleScript bridge
│ │ ├── cache-manager.ts # Caching system
│ │ ├── error-correction.ts # Error correction
│ │ └── date-handler.ts # Date formatting
│ └── types/ # TypeScript definitions
├── tests/
│ ├── unit/ # Unit tests
│ └── integration/ # Integration tests
└── dist/ # Compiled JavaScript
osascript -e 'tell application "Things3" to return name of first to do'
npm run buildnode dist/index.jsContributions are welcome! Please follow conventional commit format and ensure all tests pass before submitting pull requests.
Please log in to share your review and rating for this MCP.
Discover more MCP servers with similar functionality and use cases
by elie222
An AI‑powered email assistant that automates inbox management, enabling users to reach inbox zero fast by handling replies, labeling, archiving, unsubscribing, and providing analytics through a plain‑text prompt configuration.
by makenotion
Provides a remote Model Context Protocol server for the Notion API, enabling OAuth‑based installation and optimized toolsets for AI agents with minimal token usage.
by sooperset
MCP Atlassian is a Model Context Protocol (MCP) server that integrates AI assistants with Atlassian products like Confluence and Jira. It enables AI to automate tasks, search for information, and manage content within Atlassian ecosystems.
by ggozad
Interact with Ollama models through an intuitive terminal UI, supporting persistent chats, system prompts, model parameters, and MCP tools integration.
by nbonamy
A desktop AI assistant that bridges dozens of LLM, image, video, speech, and search providers, offering chat, generative media, RAG, shortcuts, and extensible plugins directly from the OS.
by GongRzhe
Provides tools for creating, editing, and enhancing PowerPoint presentations through a comprehensive set of MCP operations powered by python-pptx.
by GongRzhe
Creates, reads, and manipulates Microsoft Word documents through a standardized interface for AI assistants, enabling rich editing, formatting, and analysis capabilities.
by GongRzhe
Gmail-MCP-Server is a Model Context Protocol (MCP) server that integrates Gmail functionalities into AI assistants like Claude Desktop. It enables natural language interaction for email management, supporting features like sending, reading, and organizing emails.
by nspady
google-calendar-mcp is a Model Context Protocol (MCP) server that integrates Google Calendar with AI assistants. It enables AI assistants to manage Google Calendar events, including creating, updating, deleting, and searching for events.