
Things MCP Server
An MCP server that allows AI assistants like Claude Code, Claude Desktop, and Cursor to interact with Things.app on macOS, enabling task creation, updates, viewing, scheduling, and organization through natural language.
Tools
add_todo
Create a new to-do item in Things.app. Add notes, tags, checklist items, and assign to projects or areas.
add_project
Create a new project in Things.app. Add notes, tags, assign to areas, and pre-populate with initial to-dos.
update_todo
Update an existing to-do item in Things.app. Modify title, notes, scheduling, tags, checklist items, project/area assignment, and completion status.
update_project
Update an existing project in Things.app. Modify title, notes, scheduling, tags, area assignment, and completion status.
things_summary
Generate a summary of your Things database with filtering options. Returns formatted Markdown or structured JSON data for tasks, projects, areas, and tags.
export_json
Export complete Things database as structured JSON for debugging, backup, or data processing.
README
Things MCP Server
Control your Things.app tasks directly from Claude Code, Claude Desktop, Cursor, and other AI assistants using the Model Context Protocol (MCP).
What It Does
This MCP server lets AI assistants interact with your Things.app tasks on macOS. You can:
- Create new tasks and projects
- Update existing items
- View your task database with detailed summaries
- Schedule tasks for specific dates
- Organize with areas, tags, and deadlines
Quick Start
1. Get Things Authorization Token
For updating existing tasks, you need an authorization token:
- Open Things.app on macOS
- Go to Things → Preferences → General
- Check "Enable Things URLs"
- Copy the authorization token that appears
2. Configure Your AI Assistant
<details> <summary><strong>Claude Desktop</strong></summary>
Add to ~/Library/Application Support/Claude/claude_desktop_config.json
(macOS):
{
"mcpServers": {
"things": {
"command": "npx",
"args": ["@wenbopan/things-mcp"],
"env": {
"THINGS_AUTH_TOKEN": "your-token-here"
}
}
}
}
</details>
<details> <summary><strong>Cursor IDE</strong></summary>
Create .cursor/mcp.json
in your project or ~/.cursor/mcp.json
globally:
{
"things": {
"command": "npx",
"args": ["@wenbopan/things-mcp"],
"env": {
"THINGS_AUTH_TOKEN": "your-token-here"
}
}
}
</details>
3. Restart Your AI Assistant
After configuration, restart your AI assistant to load the MCP server.
Use Cases
Daily Planning
"Show me my today's tasks and create a project for the new marketing campaign with initial tasks for research, design, and content creation."
Project Management
"Update the mobile app project to add design review and testing tasks, then schedule the design review for next Monday."
Task Organization
"Move all my unscheduled shopping tasks to the 'Personal' area and tag them with 'weekend'."
Progress Tracking
"Give me a summary of all active projects with their deadlines and completion status."
Quick Capture
"Create a task to call the dentist, schedule it for tomorrow, and set a deadline for end of week."
License
MIT
Contributing
Issues and pull requests welcome! Please ensure all tests pass before submitting.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.