EARLY App MCP Server
An MCP server that provides AI assistants with access to the EARLY time tracking public API, enabling time entry management, activity management, and report generation through natural language.
README
EARLY App MCP Server
An unofficial Model Context Protocol (MCP) server that provides access to the EARLY app time tracking public API.
Overview
EARLY is a time tracking application with a comprehensive public API. This MCP server enables AI assistants to interact with time tracking data through the public EARLY API.
Tools
Time Entry Management
create_time_entry- Create a new time entry with flexible time parametersedit_time_entry- Edit an existing time entryget_time_entries- Get time entries for a date rangedelete_time_entry- Delete a time entry by IDstart_timer- Start tracking time for a projectstop_timer- Stop the currently running timerget_active_timer- Get information about the currently running timerupdate_active_timer- Update the description of the currently running timer
Activity Management
list_activities- Get all activitiescreate_activity- Create a new activity (project)update_activity- Update an existing activityarchive_activity- Archive or delete an activity
User & Reports
generate_report- Generate summary reports for time entriesget_current_user- Get current user information
Resources
Time Entries
early://time-entries/today- Today's time entries with detailed JSON dataearly://time-entries/week- Current week's time entries
Activities
early://activities- All activities (active + inactive + archived)early://activities/active- Only active activities
Quick Start
Installation
No installation required! Use npx to run the server:
npx @janfincke/early-mcp-server
Configuration (for Claude Desktop and others)
{
"mcpServers": {
"early-time-tracker": {
"command": "npx",
"args": [
"@janfincke/early-mcp-server"
],
"env": {
"EARLY_API_KEY": "your-early-api-key-here",
"EARLY_API_SECRET": "your-early-api-secret-here"
}
}
}
}
Get your API credentials from the EARLY desktop app: Settings → Developer → API Keys
Documentation
Comprehensive documentation is available at janfincke.github.io/early-mcp-server including:
- Getting Started Guide - Installation and setup
- Tools Reference - Complete documentation for all 6 tools
- Integration Guide - Claude Desktop and MCP client setup
- Troubleshooting - Common issues and solutions
EARLY API Documentation
- Base URL: https://developers.early.app/
- Documentation: Postman Collection
- Authentication: API Key (assumed)
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests
- Submit a pull request
License
MIT License - see LICENSE file for details.
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。