Tempus MCP
Enables AI assistants to manage Toggl Track time entries, projects, and workspaces through natural language, supporting CRUD operations and past date time slots.
README
Tempus MCP ⏱️
Tempus (Latin for "time") — An MCP server for Toggl Track.
A Model Context Protocol (MCP) server that provides AI assistants with full access to your Toggl Track time tracking data. Create time entries for past dates, manage projects, query workspaces, and more — all through natural language.
Tools
Time Entries
| Tool | Description |
|---|---|
toggl_list_time_entries |
List time entries with optional date filtering |
toggl_get_current_time_entry |
Get the currently running time entry |
toggl_create_time_entry |
Create time entries for any date (past or future) with project assignment, tags, and billable status |
toggl_update_time_entry |
Update existing time entries (description, project, start/stop, duration) |
toggl_delete_time_entry |
Permanently delete a time entry |
toggl_stop_time_entry |
Stop a running time entry |
Projects
| Tool | Description |
|---|---|
toggl_list_projects |
List all projects in a workspace |
toggl_get_project |
Get a single project by ID |
toggl_create_project |
Create a new project |
Workspaces & User
| Tool | Description |
|---|---|
toggl_list_workspaces |
List all accessible workspaces |
toggl_get_workspace |
Get workspace details |
toggl_get_me |
Get authenticated user profile |
toggl_list_clients |
List clients in a workspace |
Installation
npm install -g tempus-mcp
# or
npx tempus-mcp
Usage
1. Get your Toggl API Token
Go to https://track.toggl.com/profile and copy your API token.
2. Run the MCP server
export TOGGL_API_TOKEN="your_token_here"
tempus-mcp
3. Configure your MCP client
Claude Desktop:
{
"mcpServers": {
"tempus": {
"command": "tempus-mcp",
"env": {
"TOGGL_API_TOKEN": "your_token_here"
}
}
}
}
Other MCP clients: The server uses stdio transport, compatible with any MCP client.
Environment Variables
| Variable | Required | Description |
|---|---|---|
TOGGL_API_TOKEN |
✅ | Your Toggl Track API token |
TOGGL_DEFAULT_WORKSPACE_ID |
❌ | Default workspace ID for convenience |
TOGGL_BASE_URL |
❌ | API base URL (default: https://api.track.toggl.com/api/v9) |
Features
- ✅ Past date time slots — Create time entries for any date in the past
- ✅ Project assignment — Assign entries to any project
- ✅ Full CRUD — Create, read, update, delete time entries
- ✅ Billable tracking — Mark entries as billable
- ✅ Tag support — Add tags to time entries
- ✅ Running entries — Start, stop, and query current timer
Development
git clone https://github.com/Kos-M/tempus-mcp.git
cd tempus-mcp
npm install
npm run build
TOGGL_API_TOKEN=your_token npm start
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。