omnifocus-mcp
Enables AI assistants to read and write to OmniFocus database, allowing natural language task management, project creation, and GTD workflows.
README
OmniFocus MCP Server
An MCP server that lets AI assistants read and write your OmniFocus database. Talk to Claude (or any MCP client) in natural language and it handles the OmniFocus automation for you.
Personal Project Notice: A hobby project for my workflow automation. MIT licensed -- use or adapt freely, but provided as-is.
What You Can Do
Once configured, talk to your assistant naturally:
- "What do I need to do today?"
- "Show me everything that's overdue"
- "Add 'Call dentist' to my inbox, due Friday"
- "Create a project for the kitchen remodel with these tasks..."
- "I just finished a meeting, here are my notes..." (parses into tasks)
- "How's my weekly review looking?"
The server exposes four tools that cover the full OmniFocus API:
| Tool | Purpose | Operations |
|---|---|---|
omnifocus_read |
Query data | Tasks, projects, tags, perspectives, folders, export |
omnifocus_write |
Modify data | Create, update, complete, delete, batch, tag management |
omnifocus_analyze |
Analytics | Productivity stats, velocity, patterns, workflows, reviews |
system |
Diagnostics | Version info, performance metrics, cache stats |
Five built-in GTD prompts (weekly review, inbox processing, Eisenhower matrix, and more) are available via the MCP prompt protocol. See Getting Started for details.
Requirements
- macOS with OmniFocus 4.7+ (the server communicates with OmniFocus via Apple's automation APIs)
- Node.js 18+
Quick Start
git clone https://github.com/kip-d/omnifocus-mcp.git
cd omnifocus-mcp
npm install
npm run build
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"omnifocus": {
"command": "node",
"args": ["/absolute/path/to/omnifocus-mcp/dist/index.js"]
}
}
}
Claude Code
claude mcp add omnifocus -- node /absolute/path/to/omnifocus-mcp/dist/index.js
Optional: Install the GTD skill for enhanced intent recognition and workflow guidance:
ln -s /absolute/path/to/omnifocus-mcp/docs/skills/omnifocus-assistant ~/.claude/skills/omnifocus-assistant
Other Clients
Cursor, Windsurf, Cline, and Zed all support local stdio MCP servers. Use the same node dist/index.js command; refer
to each client's documentation for config file location.
Remote Access (HTTP)
The server supports HTTP transport for accessing OmniFocus from another machine (e.g., via Tailscale):
node dist/index.js --http --port 3000
See the HTTP Transport Guide for setup, authentication, and client configuration.
Documentation
| Audience | Document | Purpose |
|---|---|---|
| Users | Getting Started | First conversation, natural language |
| Users | Troubleshooting | Common issues and solutions |
| Users | Smart Capture | Parse meeting notes into tasks |
| Users | HTTP Transport | Remote access setup |
| Developers | Developer Guide | API examples, tool call formats |
| Developers | Architecture | JXA + OmniJS Bridge internals |
| Developers | API Reference | API reference versions |
| Developers | Patterns and Solutions | Symptom lookup, common fixes |
| Developers | Documentation Map | Full index of documentation |
Testing
| Suite | Command | Tests | Time |
|---|---|---|---|
| Unit | npm run test:unit |
1634 (70 files) | ~2s |
| Integration | npm run test:integration |
73 | ~4 min |
| All | npm test |
Both suites | ~4 min |
Integration tests require OmniFocus running on macOS and exercise real database queries. Timing scales with database
size (the ~4 min figure is against a ~2,500 task database). Set DISABLE_INTEGRATION_TESTS=true to skip them.
Limitations
- macOS only -- The server communicates with OmniFocus via Apple's JXA and OmniAutomation APIs, which require macOS. Remote access from other platforms is possible via HTTP transport.
See Troubleshooting for common issues.
License
MIT License -- see LICENSE file.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。