Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"things": {
"command": "~/.venvs/things3-mcp-env/bin/Things3-MCP-server"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
This Model Context Protocol (MCP) server lets you use Claude Desktop to interact with your task management data in Things 3. You can ask Claude or your MCP client of choice to create tasks, analyze projects, help manage priorities, and more.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
uvx 'Things3-MCP-server' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked Things3-MCP-server against OSV.dev.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in productivity
Dynamic problem-solving through sequential thought chains
Persistent memory using a knowledge graph
Local-first AI memory with knowledge graphs and hybrid search. 17+ AI tools via MCP. Free.
MCP server for monday.com integration.
MCP Security Weekly
Get CVE alerts and security updates for Things3 MCP and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.

This Model Context Protocol (MCP) server lets you use Claude Desktop to interact with your task management data in Things 3. You can ask Claude or your MCP client of choice to create tasks, analyze projects, help manage priorities, and more.
This MCP server leverages a combination of the Things.py library and Things 3’s AppleScript support, enabling reading and writing to Things 3.
This MCP server unlocks the power of AI for your task management:
Option A: Install from PyPI in a virtual environment (recommended)
# Create a virtual environment in your home directory
python3 -m venv ~/.venvs/things3-mcp-env
source ~/.venvs/things3-mcp-env/bin/activate
# Install the package
pip install Things3-MCP-server==2.0.6
Option B: Install from source (for development/contributors)
# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh
# Restart your terminal afterwards
# Clone and install the package with development dependencies
git clone https://github.com/rossshannon/Things3-MCP
cd Things3-MCP
uv venv
uv pip install -e ".[dev]" # Install in development mode with extra dependencies
Edit the Claude Desktop configuration file:
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
Add the Things server to the mcpServers key in the configuration file:
Option A: Using PyPI package in virtual environment
{
"mcpServers": {
"things": {
"command": "~/.venvs/things3-mcp-env/bin/Things3-MCP-server"
}
}
}
Option B: Using source installation (for development/contributors)
{
"mcpServers": {
"things": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/PARENT/FOLDER/Things3-MCP",
"run",
"Things3-MCP-server"
]
}
}
}
Restart the Claude Desktop app to enable the integration.