FocusRelayMCP

FocusRelayMCP

Fast native Swift OmniFocus MCP server and CLI for macOS. Let AI assistants safely read, update, complete, and organize tasks and projects through documented Omni Automation APIs.

Category
Visit Server

README

FocusRelay — Fast Swift OmniFocus MCP Server and CLI for macOS

Plan your day and keep OmniFocus up to date with AI

FocusRelay is a fast, native Swift MCP server and CLI that helps AI assistants read and safely update OmniFocus using documented OmniFocus APIs.

Install with Homebrew · See what it can do · Star FocusRelay · Contribute

Demo: Ask an AI assistant about your OmniFocus tasks

Ask about the work already in OmniFocus, review the answer, and make approved changes without clicking through long task lists.

Ask. Review. Update.

FocusRelay is designed for targeted questions and compact answers, so the assistant does not need your entire OmniFocus database for routine requests.

Try prompts like:

  • “How many flagged items do I have?”
  • “Show me the first three available tasks in my inbox.”
  • “Find my task called [task name], flag it, and verify the change.”
  • “Set [task name] due tomorrow at 5 PM in my local timezone and verify the change.”

These workflows were tested against the released Homebrew build with Kimi K2.7 Code, and the inbox query with a second MCP-capable model. Updates target stable OmniFocus IDs and can verify the saved result. If names are duplicated, ask to see the candidates before changing anything.

FocusRelay 0.10.0-beta can:

  • find and count tasks using dates, flags, tags, projects, availability, inbox state, completion, estimates, and text search;
  • review projects, folders, tags, task counts, and stalled work;
  • update names, notes, flags, dates, estimates, tags, project settings, and review intervals;
  • complete, reactivate, change status, and move existing tasks and projects;
  • preview a proposed change and verify the saved result.

The current beta updates existing tasks and projects. Creating or deleting items is not part of this release; creation is tracked in #82 and #83.

Why FocusRelay?

Keep the assistant focused

FocusRelay exposes 14 model-facing tools—seven for reading and seven for making supported changes. Internal diagnostics stay in the CLI, count commands avoid returning long item lists, and field selection keeps responses compact.

Native Swift speed at real-library scale

FocusRelay is compiled as native Swift and installed with Homebrew, with no Node.js or Python runtime in the request path. Single-pass filtering and early-stop pagination keep focused inbox reads near one second in testing at thousands-of-tasks scale. The same core powers a CLI for precise, low-context queries.

Run where OmniFocus understands its data

The Swift server dispatches work to a lightweight bridge plug-in that runs inside OmniFocus’s Omni Automation context. It uses documented APIs and native statuses, keeping results aligned with OmniFocus without reading its private database.

Make changes you can check

Update tools target stable IDs and support previews, per-item results, compact return fields, and optional verification. A failed save, update, or verification is reported as a failure—not success.

Validation covered thousands of tasks and thousands of measured calls without errors or timeouts in the final benchmark runs. See the 0.10.0-beta release notes for evidence and limits.

Privacy and security

FocusRelay runs locally on your Mac. Its Swift server communicates on-device with a bridge plug-in that accesses OmniFocus through documented APIs. FocusRelay has no hosted cloud service and does not send your OmniFocus data to a FocusRelay-operated service.

Your MCP client and chosen AI model may transmit tool inputs and results under their own privacy terms. Review those settings before using FocusRelay with sensitive data.

Install the OmniFocus MCP server with Homebrew

Requirements:

  • macOS on Apple silicon;
  • OmniFocus 4;
  • Homebrew;
  • an MCP-compatible assistant or a shell-capable AI agent.

1. Install and trust the formula

Homebrew 6 requires explicit trust for formulae from non-official taps. Trust only the FocusRelay formula, then install it:

brew tap deverman/focus-relay
brew trust --formula deverman/focus-relay/focusrelay
brew install focusrelay

Formula-specific trust authorizes FocusRelay without trusting every current or future formula in the tap. See Homebrew’s Tap Trust documentation for details.

2. Install the OmniFocus plugin

mkdir -p "$HOME/Library/Containers/com.omnigroup.OmniFocus4/Data/Library/Application Support/Plug-Ins"
cp -R "$(brew --prefix focusrelay)/share/focusrelay/Plugin/FocusRelayBridge.omnijs" \
  "$HOME/Library/Containers/com.omnigroup.OmniFocus4/Data/Library/Application Support/Plug-Ins/"

The plugin and binary must stay on the same version. Repeat this copy step after upgrading FocusRelay.

3. Restart OmniFocus

Quit OmniFocus completely and reopen it so the updated plugin is loaded:

osascript -e 'tell application "OmniFocus" to quit'
sleep 2
open -a "OmniFocus"

4. Add FocusRelay to your AI assistant

Configure a local stdio MCP server with:

  • command: /opt/homebrew/bin/focusrelay
  • arguments: serve

<details> <summary>OpenCode configuration example</summary>

{
  "mcp": {
    "focusrelay": {
      "type": "local",
      "command": ["/opt/homebrew/bin/focusrelay", "serve"],
      "enabled": true
    }
  }
}

</details>

On the first query, OmniFocus asks whether to allow the automation. Choose Run Script. If the prompt is hidden, bring OmniFocus to the front.

5. Check the connection

focusrelay --version
focusrelay bridge-health-check
focusrelay list-tasks --fields id,name --limit 1

Then ask:

How many flagged items do I have in OmniFocus?

<details> <summary>Manual download or source build</summary>

Download the latest binary and FocusRelayBridge.omnijs from GitHub Releases, or build with the Swift 6.3.3 toolchain selected by the checked-in .swift-version:

git clone https://github.com/deverman/FocusRelayMCP.git
cd FocusRelayMCP
swift build -c release
./scripts/install-plugin.sh

After installing the plugin, restart OmniFocus completely.

</details>

Use FocusRelay as an OmniFocus MCP server or CLI

MCP lets compatible assistants discover FocusRelay and choose the right action. The CLI is useful for scripts, debugging, and agents that already have shell access.

# Count without returning every matching task
focusrelay task-counts --flagged true

# Return only three task names
focusrelay list-tasks \
  --inbox-only true \
  --available-only true \
  --limit 3 \
  --fields name

# Preview a change without touching OmniFocus
focusrelay update-tasks <task-id> \
  --flagged true \
  --preview-only \
  --return-fields id,name,flagged

Run focusrelay --help for the command list. For write examples and safety rules, see Safe Update Workflows for CLI and MCP.

Compare FocusRelay with other OmniFocus MCP servers

FocusRelay combines a native Swift server with a bridge plug-in that executes inside OmniFocus. Swift keeps MCP fast and compact; the bridge gets fresh data and applies changes through documented OmniFocus APIs.

✅ Available · 🟡 Coming next · 🟠 Backlog · ◇ Project roadmap · — Not currently documented

Capability FocusRelay OmniFocus-MCP Enhanced OmnifocusMCP Operator
Runtime Native Swift · Homebrew TypeScript · npx TypeScript · npx Native Rust · Homebrew; Python and TypeScript available Python · uvx
OmniFocus access Bridge plug-in inside Omni Automation; documented APIs JXA and Omni Automation through osascript Omni Automation through osascript Omni Automation through osascript Internal SQLite read cache; OmniJS fallback
Public MCP tools 14 → 11 after #91, #82, and #83 12 18 45 11
Find, filter, and count tasks ✅ ✅ ✅ ✅ ✅
Update existing tasks ✅ ✅ ✅ ✅ ✅
Update existing projects ✅ ✅ ✅ ✅ ◇ v1.5 roadmap
Preview and post-save verification ✅ Every write tool; per-target results — — — —
Drop projects without deleting them ✅ ✅ — ✅ —
Create tasks and subtasks 🟡 #82 ✅ ✅ ✅ ✅
Create projects 🟡 #83, including inbox-task conversion ✅ ✅ ✅ ◇ v1.5 roadmap
Planned-date updates 🟠 #16 ✅ ✅ ✅ —
Repeating tasks 🟠 #93 ✅ — ✅ ✅
Custom perspective contents 🟠 #10 ✅ ✅ — —
Permanently delete tasks and projects — ✅ ✅ ✅ —

This comparison reflects each project’s public documentation on July 15, 2026; “Not documented” is not a claim that a feature is impossible. The other public READMEs do not describe an equivalent per-target preview and post-save verification contract.

Preview resolves IDs and validates the change without saving it. Verification runs after OmniFocus saves, reads the affected values back, and reports a mismatch as a failure. These are MCP tool arguments, so Codex, Claude Code, OpenCode, and other standard stdio MCP clients can use them; whether a model chooses them without being asked depends on the model and client. For important changes, ask it to “preview first, then apply with verification.”

Help shape FocusRelay

See GitHub Issues for planned work. If FocusRelay earns a place in your workflow, star the repository so more OmniFocus users can find it.

Want to help? Pick an issue, propose a use case, or open a focused pull request. See CONTRIBUTING.md to get started.

Troubleshooting

The bridge times out

  1. Bring OmniFocus to the front and accept the first Run Script prompt.
  2. Confirm FocusRelay Bridge is enabled under Automation → Configure Plug-ins….
  3. Recopy the plugin, quit OmniFocus completely, and reopen it.
  4. Run focusrelay bridge-health-check.

Results look stale after an upgrade

The plugin JavaScript is cached by OmniFocus. Reinstall the plugin and restart OmniFocus completely. Project and tag catalogs cache for five minutes; task queries are always fresh.

A time-based result looks wrong after travel

Restart the MCP client and OmniFocus so FocusRelay picks up the current macOS timezone.

Development

swift build
swift test

FocusRelay uses Swift Testing from the Swift toolchain. Production query changes must follow the documented Omni Automation contract.

License

FocusRelay is available under the MIT License.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured