MCP.so
Sign In

OmniFocus MCP Server

@themotionmachine

Basic information

Category

Other

License

MIT

Transports

stdio

Author

themotionmachine

About OmniFocus MCP Server

Let LLMs interface with your tasks and projects through the Model Context Protocol. Add, organize, and query your OmniFocus database with natural language commands.

OmniFocus MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "omnifocus": {
      "command": "npx",
      "args": [
        "-y",
        "omnifocus-mcp"
      ]
    }
  }
}

OmniFocus MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is OmniFocus MCP Server?

A Model Context Protocol (MCP) server that connects OmniFocus to Claude and other MCP-compatible AI assistants. It bridges natural language conversation with the OmniFocus database, allowing querying, creating, editing, and removing tasks and projects, including bulk operations.

How to use OmniFocus MCP Server?

Requires macOS with OmniFocus installed and Node.js 20 or later. Add the server to Claude Desktop’s configuration file or use claude mcp add. For other clients, launch via npx -y omnifocus-mcp over stdio. On first use, macOS will request automation access.

Key features of OmniFocus MCP Server

  • Provides 12 tools for querying, creating, editing, and removing items.
  • Supports batch operations for multiple tasks and projects.
  • Offers resources for attaching OmniFocus data as conversation context.
  • Emits structured logs via the MCP logging protocol.
  • Prefers targeted queries over full database dumps.
  • Leverages OmniFocus’s embedded Omni Automation and JXA.

Use cases of OmniFocus MCP Server

  • Translate a syllabus PDF into a fully specified project with tasks, tags, and dates.
  • Turn a meeting transcript into a list of actionable tasks.
  • Audit and reorganize tags, projects, and folders conversationally.
  • Create visualizations of tasks, projects, and tags.
  • Batch process dozens of items in a single operation.

Frequently asked questions

1

What are the dependencies and runtime requirements?

macOS with OmniFocus installed, Node.js 20 or later. No additional runtime setup beyond granting automation access once.

2

Where does the OmniFocus data live?

Data remains in the OmniFocus database; the server only reads and writes through osascript, JXA, and Omni Automation.

3

How is the server transported and authenticated?

It communicates over stdio with MCP clients. macOS handles authentication by requesting automation access on first launch.

4

What is the difference between query_omnifocus and dump_database?

`query_omnifocus` applies targeted filters and is much faster and lighter; `dump_database` returns the complete database state for comprehensive analysis.

5

Can I use the server with MCP clients other than Claude Desktop?

Yes, any MCP client that supports stdio can launch it with `npx -y omnifocus-mcp`. The configuration method varies per client.

Comments

More Other MCP servers