Things3 MCP Server Integration

What does “Things3” MCP Server do?

The Things3 MCP Server is a Model Context Protocol (MCP) server designed to provide seamless integration between AI assistants and the Things3 task management application on macOS. It empowers AI-driven workflows by exposing over 25 specialized tools for complete control over task, project, area, and tag management in Things3. Through this server, clients can automate the creation, reading, updating, deletion, and organization of tasks and projects, perform bulk operations, and utilize intelligent features such as automatic tag creation and error correction. By bridging AI systems with the Things3 ecosystem, this MCP server enhances productivity and enables sophisticated automations for personal or team task management, all while leveraging AppleScript optimization and robust error handling.

List of Prompts

No prompt templates are explicitly mentioned in the repository.

List of Resources

No explicit MCP resources are described in the repository or documentation.

List of Tools

• TODO Management Tools: Tools to create, read, update, delete, complete, and uncomplete tasks in Things3.
• Project Management Tools: Tools for creating, updating, organizing, and deleting projects.
• Area Management Tools: Tools to manage areas, including organizing and deleting them.
• Tag System Tools: Tools to create, delete, and manage hierarchical tags, including bulk tag operations.
• Bulk Operations Tools: Tools to move or update multiple items (tasks, projects, etc.) at once.
• Logbook Search Tool: Tool to search completed items in the Things3 logbook with date range filtering.
• Automatic Tag Creation: Automatically creates tags when referenced in operations.
• Error Correction Tool: Automatically fixes common issues like date conflicts and missing titles.

Use Cases of this MCP Server

• Automated Task Management: AI agents can create, update, complete, or delete tasks in Things3, streamlining personal productivity workflows.
• Project and Area Organization: Developers or teams can automatically organize projects and areas, manage their lifecycle, and ensure all items are structured according to custom logic.
• Bulk Task Operations: Perform mass updates, moves, or completions of tasks and projects, saving time on routine maintenance.
• Intelligent Tagging: Automatically generate and assign tags to tasks and projects, ensuring consistent organization and retrieval.
• Advanced Logbook Searches: Search and analyze completed items with date filtering, enabling retrospective reviews and reporting for productivity analysis.

How to set it up

Windsurf

1. Ensure you have Node.js (>= 16.0.0) and Things3 installed on macOS.
2. Obtain or generate a Things3 authentication token.
3. Locate your Windsurf configuration file.
4. Add the Things3 MCP Server using the following JSON snippet:

   {
     "mcpServers": {
       "things3": {
         "command": "npx",
         "args": ["things3-mcp@latest"],
         "env": {
           "THINGS3_AUTH_TOKEN": "your_auth_token_here"
         }
       }
     }
   }
   

5. Save the configuration and restart Windsurf.
6. Verify that the server is running and connected.

Claude

1. Make sure Node.js (>= 16.0.0) and Things3 are installed on macOS.
2. Acquire your Things3 auth token.
3. Open the Claude configuration file.
4. Insert the following under the mcpServers section:

   {
     "mcpServers": {
       "things3": {
         "command": "npx",
         "args": ["things3-mcp@latest"],
         "env": {
           "THINGS3_AUTH_TOKEN": "your_auth_token_here"
         }
       }
     }
   }
   

5. Save your changes and restart Claude.
6. Confirm server accessibility.

Cursor

1. Install Node.js (>= 16.0.0) and ensure Things3 is set up on macOS.
2. Generate a Things3 authentication token.
3. Edit the Cursor configuration JSON.
4. Add the Things3 MCP Server definition:

   {
     "mcpServers": {
       "things3": {
         "command": "npx",
         "args": ["things3-mcp@latest"],
         "env": {
           "THINGS3_AUTH_TOKEN": "your_auth_token_here"
         }
       }
     }
   }
   

5. Save and restart Cursor.
6. Check that the server is active.

Cline

1. Ensure Node.js (>= 16.0.0) and the Things3 app are present on your macOS system.
2. Set up your Things3 auth token.
3. Locate and open the Cline configuration file.
4. Add the following to the mcpServers object:

   {
     "mcpServers": {
       "things3": {
         "command": "npx",
         "args": ["things3-mcp@latest"],
         "env": {
           "THINGS3_AUTH_TOKEN": "your_auth_token_here"
         }
       }
     }
   }
   

5. Save, restart Cline, and verify Things3 MCP Server connectivity.

Securing API Keys

Always secure your Things3 authentication token by using environment variables, as shown in the configuration examples above. Never hard-code secrets in code repositories.

Example:

{
  "mcpServers": {
    "things3": {
      "command": "npx",
      "args": ["things3-mcp@latest"],
      "env": {
        "THINGS3_AUTH_TOKEN": "your_auth_token_here"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "things3": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “things3” to your actual server name if different, and update the URL accordingly.

Overview

Based on the above tables, the Things3 MCP Server is well-implemented in terms of tools and integration instructions, but lacks standardized prompt templates, explicit MCP resources, and details on advanced MCP features like roots and sampling. For a single-purpose integration, it’s solid but could be improved with richer protocol features.

MCP Score

Overall rating: 5/10
This MCP server is robust for its purpose (Things3 integration), with strong tool coverage and clear setup, but lacks depth in standard MCP resources, prompt templates, and advanced MCP features, making it a good but not exemplary MCP implementation.