FocusRelay
Talk to your OmniFocus tasks. An OmniFocus MCP server that lets AI assistants query your tasks, projects, and tags using natural language—no more clicking through endless lists.
What is FocusRelay?
FocusRelay is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to talk to your omnifocus tasks. an omnifocus mcp server that lets ai assistants query your tasks, projects, and tags using natural language—no more clicking through endless lists.
Talk to your OmniFocus tasks. An OmniFocus MCP server that lets AI assistants query your tasks, projects, and tags using natural language—no more clicking through endless lists.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Talk to your OmniFocus tasks. An OmniFocus MCP server that l
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx focusrelaymcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use FocusRelay
FocusRelayMCP is a native macOS MCP server that connects AI assistants to OmniFocus, the powerful task manager for Mac and iOS. It exposes both read and write tools — letting you query tasks by due date, tags, or project, mark items complete, move tasks between projects, and update project statuses — all through natural language conversation. Mac users who rely on OmniFocus for GTD or complex project management use FocusRelayMCP to review and manage their work without interrupting their focus or navigating OmniFocus's interface manually.
Prerequisites
- macOS (the server is a native Swift binary; not available on Linux or Windows)
- OmniFocus 3 or later installed from the Mac App Store
- Homebrew installed for the recommended installation method
- An MCP-compatible client such as Claude Desktop or opencode
Install FocusRelay via Homebrew
Tap the deverman Homebrew repository and install the focusrelay binary. This installs the native Swift server that communicates with OmniFocus through its Automation scripting interface.
brew tap deverman/focus-relay
brew install focusrelayInstall the OmniFocus plugin
FocusRelayMCP requires an OmniFocus plugin to expose the automation API. Follow the installation instructions in the repository to install the plugin file into OmniFocus.
Restart OmniFocus and approve the security dialog
After installing the plugin, restart OmniFocus. It will display a security dialog asking you to approve the plugin — you must click Approve for the MCP server to communicate with OmniFocus.
Configure your MCP client
Add focusrelay to your MCP client configuration. Point the command to the Homebrew-installed binary and use the 'serve' subcommand.
Restart your MCP client and verify
Restart Claude Desktop or your client. Ask Claude 'What tasks are due today?' to confirm FocusRelayMCP is connected and reading from OmniFocus successfully.
FocusRelay Examples
Client configuration
Claude Desktop or opencode configuration pointing to the Homebrew-installed focusrelay binary. Use the path from `brew --prefix` if different from the default.
{
"mcpServers": {
"focusrelay": {
"command": "/opt/homebrew/bin/focusrelay",
"args": ["serve"]
}
}
}Prompts to try
Natural language prompts to query and manage your OmniFocus tasks through Claude once FocusRelayMCP is connected.
- "What should I be doing today?"
- "Show me all overdue tasks across my projects"
- "What projects have no next actions?"
- "Mark the 'Send invoice' task as complete"
- "Move all tasks tagged 'waiting' to the On Hold project"
- "How many tasks did I complete this week?"Troubleshooting FocusRelay
No tasks are returned and Claude says it cannot connect to OmniFocus
Ensure OmniFocus is running and that you approved the security/automation plugin dialog after installing the plugin. If you dismissed the dialog, re-open OmniFocus > Plugins and manually enable the FocusRelay plugin.
'focusrelay: command not found' after Homebrew installation
Run `brew link focusrelay` to ensure the binary symlink is created in /opt/homebrew/bin. Also confirm /opt/homebrew/bin is in your PATH. Use the full path `/opt/homebrew/bin/focusrelay` in the MCP config as a workaround.
Write operations (update_tasks, move_tasks) silently fail
OmniFocus Automation requires explicit permission. Open OmniFocus > Settings > Automation and verify that the FocusRelay plugin has both read and write permissions. On macOS Ventura+, also check System Settings > Privacy & Security > Automation.
Frequently Asked Questions about FocusRelay
What is FocusRelay?
FocusRelay is a Model Context Protocol (MCP) server that talk to your omnifocus tasks. an omnifocus mcp server that lets ai assistants query your tasks, projects, and tags using natural language—no more clicking through endless lists. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install FocusRelay?
Follow the installation instructions on the FocusRelay GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with FocusRelay?
FocusRelay works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is FocusRelay free to use?
Yes, FocusRelay is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
FocusRelay Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to FocusRelay? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up FocusRelay in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use FocusRelay?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.