经 AI Skill Hub 精选评估,FocusRelayMCP 获评「强烈推荐」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.0 分,适合有一定技术背景的用户使用。
FocusRelayMCP 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
FocusRelayMCP 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/deverman/FocusRelayMCP
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"focusrelaymcp": {
"command": "npx",
"args": ["-y", "focusrelaymcp"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 FocusRelayMCP 执行以下任务... Claude: [自动调用 FocusRelayMCP MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"focusrelaymcp": {
"command": "npx",
"args": ["-y", "focusrelaymcp"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Requirements:
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.
Run the installed setup command:
focusrelay setup
It finds the Homebrew-bundled plug-in, verifies that its version matches the binary, detects every supported OmniFocus plug-in folder, and previews the source and destinations before asking permission to copy anything. Existing plug-ins remain in place until their replacement has been copied successfully. Rerunning setup reports copies that are already current.
Setup also prints the client-neutral MCP command and arguments. Add --client claude-code, --client codex, or --client opencode for a known client example; FocusRelay prints the configuration but does not edit it.
For automation, review the same plan first and then opt in explicitly:
focusrelay setup --dry-run
focusrelay setup --non-interactive
Building from source? Continue using ./scripts/install-plugin.sh; it is a thin development entry point for this same Swift setup implementation.
focusrelay workflow list focusrelay workflow get process_inbox
Upgrading the Homebrew formula replaces the binary but leaves the copies of the plugin already installed for OmniFocus untouched, so a skipped step 2 can strand the plugin many releases behind.
Run guided setup again, restart OmniFocus, and check the loaded version:
```bash focusrelay setup
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](https://github.com/themotionmachine/OmniFocus-MCP) | [Enhanced](https://github.com/jqlts1/omnifocus-mcp-enhanced) | [OmnifocusMCP](https://github.com/vitalyrodnenko/OmnifocusMCP) | [Operator](https://github.com/HelloThisIsFlo/omnifocus-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 | **9, with seven read tools plus edit_tasks and edit_projects; 11 after planned creation tools [#82](https://github.com/deverman/FocusRelayMCP/issues/82) and [#83](https://github.com/deverman/FocusRelayMCP/issues/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](https://github.com/deverman/FocusRelayMCP/issues/82) | ✅ | ✅ | ✅ | ✅ |
| Create projects | 🟡 [#83, including inbox-task conversion](https://github.com/deverman/FocusRelayMCP/issues/83) | ✅ | ✅ | ✅ | ◇ v1.5 roadmap |
| Planned-date updates | 🟠 [#16](https://github.com/deverman/FocusRelayMCP/issues/16) | ✅ | ✅ | ✅ | — |
| Repeating tasks | 🟠 [#93](https://github.com/deverman/FocusRelayMCP/issues/93) | ✅ | — | ✅ | ✅ |
| Custom perspective contents | 🟠 [#10](https://github.com/deverman/FocusRelayMCP/issues/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.”
FocusRelayMCP 是专为 macOS 版 OmniFocus 设计的 Model Context Protocol (MCP) 服务端。它允许用户通过 Claude 等 AI 助手,使用自然语言直接查询 OmniFocus 中的任务、项目和标签。通过该工具,你可以像聊天一样询问“我今天该做什么?”,AI 将为你实时过滤并呈现结果,实现任务管理的智能化升级。
FocusRelayMCP 提供强大的自然语言查询能力,支持基于时间周期的智能过滤。它具备项目健康度检测功能,能自动识别停滞的项目或缺失 Next Action 的任务。此外,它还具备上下文感知能力,支持通过标签、截止日期(Due Date)、延迟日期(Defer Date)及完成日期进行精准筛选,并能自动识别本地时区,确保任务处理的准确性。
安装过程分为四个核心步骤:首先,通过 Homebrew(推荐)、手动下载或源码编译的方式安装 focusrelay 二进制文件;其次,安装配套的 OmniFocus 插件;第三,在你的 MCP 客户端中进行配置;最后,重启 OmniFocus 以使设置生效。对于 macOS 用户,推荐使用 `brew install focusrelay` 进行快速部署。
除了通过 AI 助手进行交互外,`focusrelay` 二进制文件还提供了命令行界面(CLI)工具,其功能与 MCP 工具集完全对应。你可以通过运行 `focusrelay --help` 查看完整的命令列表,并根据实际需求执行相应的命令行操作,实现灵活的任务管理。
配置 MCP 服务时,需根据安装方式修改配置文件(如 `opencode.json` 或 Claude Desktop 的配置文件)。如果你是通过 Homebrew 安装的,请在配置中指定正确的本地路径(如 `/opt/homebrew/bin/focusrelay`)并启用 `serve` 命令。如果是开发者通过源码构建,则需指向对应的构建路径。
项目包含自动化脚本模块,开发者可以使用 `./scripts/package-plugin.sh` 来打包插件,确保插件分发的一致性。整体工作流通过 MCP 协议将 AI 客户端、FocusRelayMCP 服务端与 OmniFocus 插件三者连接,构建起从自然语言指令到本地任务操作的完整闭环。
针对常见的“Bridge timed out”或“Plugin not responding”错误,通常由两个原因引起:一是缺少安全权限,请务必在 OmniFocus 的安全对话框中点击“Run Script”以授权;二是插件失效,此时需要重新运行 `./scripts/install-plugin.sh` 脚本进行修复。
高质量的MCP工具,实现了OmniFocus任务与AI助手的对话
该工具未明确声明开源协议,商业使用前请联系原作者确认授权范围,避免侵权风险。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
AI Skill Hub 点评:FocusRelayMCP 的核心功能完整,质量优秀。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | FocusRelayMCP |
| 原始描述 | 开源MCP工具:Talk to your OmniFocus tasks. An OmniFocus MCP server that lets AI assistants qu。⭐26 · Swift |
| Topics | aiautomationswiftmacos |
| GitHub | https://github.com/deverman/FocusRelayMCP |
| 语言 | Swift |
收录时间:2026-06-02 · 更新时间:2026-06-02 · License:未公布 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端