Let LLMs interface with your tasks and projects through the Model Context Protocol. Add, organize, and query your OmniFocus database with natural language commands.
# Add to your Claude Code skills
git clone https://github.com/themotionmachine/OmniFocus-MCPA Model Context Protocol (MCP) server that integrates with OmniFocus to enable Claude (or other MCP-compatible clients) to interact with your tasks and projects.

This MCP server creates a bridge between AI assistants (like Claude) and your OmniFocus task management system. It gives AI models the ability to view, create, edit, and remove tasks and projects in your OmniFocus database through natural language conversations. Some ways you could use it:
Known Issues
resource and prompt featuresplanned date type in Omnifocus 4.7~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"omnifocus": {
"command": "npx",
"args": ["-y", "omnifocus-mcp"]
}
}
}
Use the new query_omnifocus tool for fast, targeted searches:
"Show me tasks due today" "Get all flagged items in my Work project"
"Count how many tasks are in each project"
"I want every task to have an energy level tag. Show me a list of all the tasks that don't have an energy level tag and your suggestions for what tag to add. I'll make any changes I think are appropriate. Then make the changes in OmniFocus."
"Ok, thanks for the detailed explanation of why the rule of law is important. Add a recurring task to my activism project that reminds me to call my representative weekly. Include a summary of this conversation in the notes field."
Get a summary of your current tasks and manage them conversationally:
"Show me all my flagged tasks due this week"
Or create custom views:
"What are my next actions in the Work folder?"
List and view your perspectives:
"What perspectives do I have available?" "Show me what's in my Inbox perspective" "Get the flagged items from my current perspective"
Extract action items from meeting transcripts, a...