tyme-mcp
Connects AI assistants to the Tyme macOS app to manage time tracking, projects, and tasks via natural language. It uses native AppleScript and JXA to control timers and generate reports without requiring cloud dependencies or API keys.
README
tyme-mcp
An MCP (Model Context Protocol) server that connects AI assistants to Tyme, the macOS time tracking app. Control timers, manage projects and tasks, search time records, and generate reports — all through natural language.
Features
- Timer control — Start, stop, and check running timers
- Project & task management — List, create, update, and delete projects and tasks
- Time record search — Query records by date range, project, task, type, and more
- Reports — Daily summaries and date-range reports grouped by project
- Native macOS integration — Communicates directly with Tyme via AppleScript/JXA. No API keys, no cloud dependency, works offline
- 22 tools covering the full Tyme workflow
Requirements
Setup
1. Install Bun (if not installed)
curl -fsSL https://bun.sh/install | bash
2. Clone and install
git clone https://github.com/cdgrph/tyme-mcp.git
cd tyme-mcp
bun install
3. Configure your MCP client
Claude Code
Add to your project's .mcp.json:
{
"mcpServers": {
"tyme": {
"command": "bun",
"args": ["run", "/path/to/tyme-mcp/src/index.ts"]
}
}
}
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"tyme": {
"command": "bun",
"args": ["run", "/path/to/tyme-mcp/src/index.ts"]
}
}
}
Replace /path/to/tyme-mcp with the actual path where you cloned the repository.
4. Launch Tyme
Make sure Tyme is running before using the MCP server. The server communicates with Tyme through macOS scripting, so Tyme must be open.
Tools
Timer Operations
| Tool | Description |
|---|---|
start_timer |
Start a timer for a task |
stop_timer |
Stop a timer for a task |
get_running_timers |
List currently running timers |
Data Retrieval
| Tool | Description |
|---|---|
list_categories |
List all categories |
list_projects |
List projects (optionally filtered by category) |
list_tasks |
List tasks in a project |
list_subtasks |
List subtasks of a task |
get_task_detail |
Get detailed task information |
get_selected_object |
Get the currently selected item in Tyme UI |
get_task_records |
Search time records by date range and filters |
get_record_detail |
Get detailed record information |
CRUD Operations
| Tool | Description |
|---|---|
create_project |
Create a new project |
update_project |
Update project properties |
delete_project |
Delete a project |
create_task |
Create a new task |
update_task |
Update task properties |
delete_task |
Delete a task |
create_record |
Create a time record |
update_record |
Update a time record |
delete_record |
Delete a time record |
Reports
| Tool | Description |
|---|---|
get_daily_summary |
Work summary for a specific day |
get_range_summary |
Work summary over a date range, grouped by project |
Usage Examples
Once configured, you can interact with Tyme using natural language:
- "Show me my projects" — lists all Tyme projects
- "What timers are running?" — checks active timers
- "Start tracking time on task X" — starts a timer
- "How much did I work this week?" — generates a summary report
- "Create a new task called 'Design review' in project Y" — creates a task
How It Works
AI Assistant → MCP Protocol → tyme-mcp → osascript (AppleScript/JXA) → Tyme.app
The server uses two scripting approaches:
- JXA (JavaScript for Automation) for read operations — returns structured JSON
- AppleScript for write operations — reliable object creation and manipulation
All user inputs are sanitized before interpolation into scripts to prevent injection.
Development
# Run the server directly
bun run src/index.ts
# Watch mode
bun run dev
Tech Stack
- Bun — TypeScript runtime
- @modelcontextprotocol/sdk — MCP server SDK
- Zod — Input validation
- AppleScript / JXA — macOS automation
License
MIT
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。