Unlock AI-powered task management with Things MCP server for seamless project and productivity control
The Things MCP Server enables seamless interaction between Claude Desktop and the Things app, empowering users to leverage natural language processing (NLP) capabilities for task management. This server leverages the Things.py library and the Things URL Scheme to provide robust features such as task creation, analysis, project management, and more.
The Things MCP Server supports a wide range of capabilities, including:
The server is built on the Model Context Protocol (MCP), which provides a standardized way for AI applications to interact with various tools and data sources. The implementation involves two key components:
things_server.py
- A traditional implementation that uses basic MCP server patterns.things_fast_server.py
- A modern implementation using the FastMCP pattern for cleaner, more maintainable code with decorator-based tool registration.Prerequisites
Installation
pip install things-mcp
Or using uv
:
uv pip install things-mcp
Running the Server
After installation, you can run the server directly:
things-mcp
Prerequisites
Step 1: Install uv
Install uv
if you haven't already:
curl -LsSf https://astral.sh/uv/install.sh | sh
Restart your terminal afterwards.
Step 2: Clone this Repository
git clone https://github.com/hald/things-mcp
cd things-mcp
Step 3: Set Up Python Environment and Dependencies
uv venv
uv pip install -r pyproject.toml
Step 4: Configure Things Authentication Token
Run the configuration tool to set up your Things authentication token:
python configure_token.py
This will guide you through the process of configuring your Things authentication token, which is required for the MCP server to interact with your Things app.
Step 5: Integrate with Claude Desktop
Edit the mcp
configuration in your ~/.config/Claude/config.json
:
{
"mcpServers": {
"things": {
"command": "uv",
"args": ["-y", "./path/to/things_server.py"],
"env": {
"TOKEN": "<YOUR-TOKEN>"
}
}
}
}
Task Creation and Management
Users can create tasks using natural language inputs, such as:
Claude: Reminder: "Book flight to NYC for the conference" due by next Friday at 5 PM.
Data Analysis and Reporting
Analyze project progress and productivity metrics with Claude:
Claude: Provide a summary report of recent projects, focusing on those over budget.
The Things MCP Server supports integration with multiple MCP clients, including:
MCP Client | Resources | Tools | Prompts |
---|---|---|---|
Claude Desktop | ✅ | ✅ | ✅ |
Continue | ✅ | ✅ | ✅ |
Cursor | ❌ | ✅ | ❌ |
This table outlines the compatibility and performance of various tools with the Things MCP Server:
Tool/Library | Compatibility Status |
---|---|
Things | Full |
Things.py | Full |
FastMCP | Partial (FastMCP) |
Logging
All errors are logged and returned with descriptive messages. To review the MCP logs from Claude Desktop, run:
tail -n 20 -f ~/Library/Logs/Claude/mcp*.log
Security Considerations
Ensure that your authentication token is kept secure by using environment variables or secure configuration files.
How do I set up the Things MCP Server for use with Claude Desktop?
What tools are supported by the Things MCP Server?
Can I use the Things MCP Server with both the standard implementation and the FastMCP version simultaneously?
mcp
settings.What is the best way to troubleshoot connectivity issues between Claude Desktop and the Things MCP Server?
How do I update the Things MCP Server to a newer version if available from PyPI?
Use pip
or uv pip
commands to install the latest version:
uv pip install --upgrade things-mcp
The project uses pyproject.toml
for dependency management and build configuration. Contributions are welcome, and developers can set up a development environment by following these steps:
Clone the Repository:
git clone https://github.com/hald/things-mcp.git
cd things-mcp
Set Up Virtual Environment with Dev Dependencies:
uv venv
uv pip install -e ".[dev]"
Run the Development Server:
Test the server with:
mcp dev things_fast_server.py
# or
mcp dev things_server.py
Build and Publish to PyPI:
If you want to package the application for distribution, run:
python -m build
twine upload dist/*
For more information about the Model Context Protocol (MCP), visit:
The Things MCP Server is a powerful tool for enhancing AI application integration through the Model Context Protocol. By providing seamless task management and analysis capabilities, it empowers users to streamline their workflows and optimize productivity.
By integrating this server with Claude Desktop and other MCP clients, you can unlock advanced features and improve your overall workflow efficiency. Explore the documentation, contribute to the project, or dive into real-world use cases to see its full potential in action.
RuinedFooocus is a local AI image generator and chatbot image server for seamless creative control
Simplify MySQL queries with Java-based MysqlMcpServer for easy standard input-output communication
Learn to set up MCP Airflow Database server for efficient database interactions and querying airflow data
Build stunning one-page websites track engagement create QR codes monetize content easily with Acalytica
Explore CoRT MCP server for advanced self-arguing AI with multi-LLM inference and enhanced evaluation methods
Access NASA APIs for space data, images, asteroids, weather, and exoplanets via MCP integration