Early MCP Server
A Model Context Protocol server for the Early time tracking API, enabling natural language time tracking, activity management, and report generation.
README
Early MCP Server
A complete Model Context Protocol (MCP) server for Early (formerly Timeular) time tracking API v4.
Use natural language to track time, manage activities, generate reports, and more—directly from Claude.
Quick Start
1. Get API Credentials
- Go to Early Account Settings
- Scroll to the bottom to find the API section
- Generate your API Key and API Secret
2. Install
git clone https://github.com/weichselbaum/early-mcp.git
cd early-mcp
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
3. Configure Claude Desktop
Add to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"early": {
"command": "/absolute/path/to/early-mcp/venv/bin/python",
"args": ["/absolute/path/to/early-mcp/early_mcp.py"],
"env": {
"EARLY_API_KEY": "your_api_key_here",
"EARLY_API_SECRET": "your_api_secret_here"
}
}
}
}
4. Restart Claude Desktop
The Early tools should now appear in Claude.
Usage Examples
Start tracking:
"Start tracking on LWX"
Check current timer:
"What am I working on?"
Stop with note:
"Stop tracking, note: finished feature implementation"
Log time manually:
"Log 2 hours on Meeting yesterday from 2pm to 4pm"
Weekly report:
"Show me my time report for last week"
Manage tags:
"Create a tag called 'urgent' in my Income folder"
Features
46 tools covering the complete Early API:
| Category | Tools | Description |
|---|---|---|
| User | 2 | Get current user, list team users |
| Tracking | 5 | Start, stop, edit, cancel, get current |
| Time Entries | 5 | List, get, create, edit, delete |
| Activities | 5 | List, create, edit, archive, unarchive |
| Folders | 10 | Full CRUD + member management |
| Tags | 4 | List, create, update, delete |
| Mentions | 3 | Create, update, delete |
| Leaves | 5 | Create, approve, deny, delete |
| Webhooks | 5 | List events, subscribe, unsubscribe |
| Reports | 2 | Generate report, today summary |
API Notes
Time Formats
All times use ISO 8601: 2024-01-15T14:30:00.000
Minimum Duration
Time entries require at least 1 minute duration.
Tags & Mentions in Notes
Special syntax for notes:
- Tags:
<{{|t|TAG_ID|}}> - Mentions:
<{{|m|MENTION_ID|}}>
Development
# Run locally
python early_mcp.py
# Test with MCP Inspector
npx @modelcontextprotocol/inspector python early_mcp.py
License
MIT - see LICENSE
API Documentation
The docs/ folder contains reference documentation for developers who want to understand the Early API or build custom implementations:
- EARLY_API_V4_REFERENCE.md - Markdown reference covering all endpoints, parameters, and response formats
- early_api_v4_collection.json - Full Postman collection export
How the docs were sourced
The JSON collection was exported from Early's official Postman workspace. Click "Run in Postman" (top right), fork the collection to your own workspace, then export as JSON. The collection is maintained by Timeular (Early's parent company).
Links
Roadmap
See ROADMAP.md for planned features and ideas. Feedback welcome!
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。