Terminal and OS · MCP server
FocusRelay: MCP server, setup and security
FocusRelay is an open-source MCP server published on GitHub that lets an AI agent find, review and safely update OmniFocus tasks and projects. Its repository has 55 stars and its last commit is from October 17, 2026 and it is licensed under MIT.
| Adoption (stars) | 17/40 | |
|---|---|---|
| Maintenance | 30/30 | |
| Framework (licence, registry, official) | 15/30 |
What FocusRelay does
According to its repository: “Connect AI tools to OmniFocus on macOS to find, review, and safely update tasks and projects.”
The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. FocusRelay is listed under Terminal and OS, a category of 115 servers in the directory, where it ranks #88 by stars.
Topics declared by the repository: automation, claude, macos, omnifocus, productivity, swift.
Installing and connecting FocusRelay
No package or remote server is declared in the official MCP registry: you install it from source, following the repository README.
It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: Swift.
Security: what to check
Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.
Points found for FocusRelay:
- System access: the Terminal and OS category gives the agent control over files, a terminal, code or a browser. A booby-trapped instruction in content the agent reads (prompt injection) can then turn into an action.
Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.
Project activity and maintenance
Created on January 30, 2026, the deverman/FocusRelayMCP repository has 55 stars and 7 forks, with 24 open issues. It has more stars than 54% of the servers in the directory. It received changes this month. Version published in the registry: 0.10.0-beta (July 15, 2026).
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
FocusRelay is a reasonable choice; check the points below before connecting it.
Strengths
- Active project: recent commit
- Listed in the official MCP registry
- Permissive licence (MIT)
Limitations
- Install from source
Avoid if…
- You cannot isolate the agent (sandbox, container)
Alternatives
- Oh My Posh Validator23.6K ★
- REA377.2K ★
- XERJ15.2K ★
- Windows MCP10.2K ★
- Microsoft Learn MCP2K ★
- NotFair4.1K ★
Learn more
Frequently asked questions
How do I install FocusRelay?
No package is declared in the MCP registry: clone the deverman/FocusRelayMCP repository, follow its README, then declare the start command in your client's MCP configuration.
Is FocusRelay free?
The code is published under the MIT licence and can be used free of charge.
Is FocusRelay safe?
Points to watch: system access. Give it minimum rights and approve sensitive actions.
Is it an official server?
Nothing says so: it is a project published by deverman on GitHub. Check who maintains it before giving it access.
What are the alternatives to FocusRelay?
In the same category: Oh My Posh Validator, REA, XERJ, and Windows MCP. Oh My Posh Validator and REA score higher on our grid.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score